© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9283
    Prev
    Next
    INDEX
    Explanations

    language characteristic of product descriptions/marketing material for electronic devices, particularly tablets.

    oai_token-act-pair · gemini-2.0-flash

    software development terms

    np_token-act-pair-logits · gpt-4o-mini

    device specifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intStringLen
    -0.60
    cope
    -0.59
    POSURE
    -0.58
     émer
    -0.58
     viewType
    -0.56
    quedas
    -0.54
    цездатний
    -0.54
    KURZBESCHREIBUNG
    -0.52
     tecnici
    -0.52
     Sarm
    -0.52
    POSITIVE LOGITS
    KommentareTeilen
    0.65
     MainAxisSize
    0.54
    AutoField
    0.54
    denly
    0.51
    ographia
    0.51
    ipel
    0.48
    SequentialGroup
    0.48
     app
    0.47
    DropTable
    0.47
    indd
    0.47
    Activations Density 0.880%

    No Known Activations