© 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. 12628
    Prev
    Next
    INDEX
    Explanations

    the word "road"

    oai_token-act-pair · gemini-2.0-flash

    road

    np_max-act · gemini-2.0-flash

    road

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Monfieur
    -0.92
     htons
    -0.83
     @"";
    -0.82
     ARXIV
    -0.82
     avoient
    -0.82
    mybatisplus
    -0.77
     HasFactory
    -0.76
    ngdoc
    -0.75
     Poitiers
    -0.75
     Lastly
    -0.75
    POSITIVE LOGITS
    '
    0.63
    ***********/
    0.53
    punten
    0.53
    före
    0.52
    PRM
    0.49
    hæng
    0.49
    Решение
    0.48
     /*
    0.48
    /*
    0.47
    stalline
    0.46
    Activations Density 0.620%

    No Known Activations