© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4659
    Prev
    Next
    INDEX
    Explanations

    "didn't" and its variants, indicating negation or lack of action

    oai_token-act-pair · gemini-2.0-flash

    Didn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    :✨
    -0.90
    neſs
    -0.88
     Diſ
    -0.86
    ^(@)
    -0.86
    ſelf
    -0.85
    */;
    -0.82
     gyhoeddwyd
    -0.82
    ChildScrollView
    -0.82
     Anſ
    -0.82
    migrationBuilder
    -0.80
    POSITIVE LOGITS
    C
    0.52
    F
    0.49
    ll
    0.47
    Enders
    0.47
    O
    0.44
    vatar
    0.44
     numeros
    0.44
    La
    0.43
     MotionEvent
    0.42
     olmayan
    0.42
    Activations Density 0.117%

    No Known Activations