© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12995
    Prev
    Next
    INDEX
    Explanations

    code with periods following variable definitions and list manipulations

    oai_token-act-pair · gemini-2.0-flash

    unique object or list identifiers

    np_token-act-pair-logits · gpt-4o-mini
    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
     to
    -0.65
    .
    -0.61
     
    -0.60
     D
    -0.57
     S
    -0.53
     M
    -0.52
     u
    -0.52
     C
    -0.52
     i
    -0.51
     m
    -0.51
    POSITIVE LOGITS
     myſelf
    1.09
    rungsseite
    1.07
     itſelf
    1.06
     raiſ
    1.04
    Hochspringen
    1.02
    ſelves
    0.99
     preſent
    0.99
     Monfieur
    0.97
     faſt
    0.97
     يتيمه
    0.97
    Activations Density 0.528%

    No Known Activations