© 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. 2256
    Prev
    Next
    INDEX
    Explanations

    acronyms, some related to lab work and processes, and some seemingly random

    oai_token-act-pair · gemini-2.0-flash

    unique linguistic patterns or formatting

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

    Scientific/technical texts

    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
    WriteAttribute
    -0.55
    Y
    -0.54
    o
    -0.43
    mp
    -0.40
    AFFIRMED
    -0.40
    stal
    -0.40
    lu
    -0.40
    tu
    -0.39
    mat
    -0.38
    oOo
    -0.38
    POSITIVE LOGITS
     themſelves
    0.81
     raiſ
    0.71
     fevere
    0.71
     itſelf
    0.71
     $_(
    0.70
     Jefus
    0.70
     whoſe
    0.68
     myſelf
    0.67
    BibitemShut
    0.66
     Theſe
    0.65
    Activations Density 2.245%

    No Known Activations