© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16288
    Prev
    Next
    INDEX
    Explanations

    the substring "di"

    oai_token-act-pair · gemini-2.0-flash

    di

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     
    -0.59
    NameValuePair
    -0.58
    chik
    -0.57
    MLLoader
    -0.57
    dbo
    -0.56
     double
    -0.54
    dout
    -0.53
    inspace
    -0.53
    istocene
    -0.53
     Mon
    -0.53
    POSITIVE LOGITS
     VizieR
    0.71
     estekak
    0.58
     utafitiHapana
    0.58
    uxxxx
    0.58
     élas
    0.54
     Anſ
    0.54
     HasFactory
    0.54
     Theſe
    0.54
     Monfieur
    0.52
     समीक्षाओं
    0.52
    Activations Density 0.346%

    No Known Activations