© 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. 9799
    Prev
    Next
    INDEX
    Explanations

    the word "is" sometimes near the word "this"

    oai_token-act-pair · gemini-2.0-flash

    the word "is"

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

    is

    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
    argout
    -0.60
     ―――――
    -0.56
    neſs
    -0.55
     Theſe
    -0.55
    eabouts
    -0.55
    .';
    -0.54
     ity
    -0.54
     departament
    -0.54
     XNUMX
    -0.53
     sini
    -0.52
    POSITIVE LOGITS
     where
    0.72
     how
    0.69
     BoxFit
    0.69
     why
    0.67
     the
    0.67
     صوتيه
    0.65
    LookAnd
    0.63
    EndInit
    0.63
    Билгалдахарш
    0.62
    Gweler
    0.60
    Activations Density 5.293%

    No Known Activations