© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5725
    Prev
    Next
    INDEX
    Explanations

    words related to stories, murders, puzzles, mysteries and investigations.

    oai_token-act-pair · gemini-2.0-flash

    narratives and perspectives

    np_max-act-logits · gemini-2.0-flash

    story

    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_18/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.18.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
    UnknownFieldSet
    -0.69
     "..\..\
    -0.62
    `;
    -0.55
     "..\..\..\
    -0.54
    èze
    -0.50
    حياته
    -0.49
    _;
    -0.49
    ್ಯ
    -0.49
    anyu
    -0.48
    enzio
    -0.48
    POSITIVE LOGITS
     betweenstory
    0.69
     <<<<<<<<<<<<<<
    0.65
     שוליים
    0.61
     Infórmanos
    0.55
    fromnode
    0.55
     conmigo
    0.54
     CURIAM
    0.54
     متعلقه
    0.53
     Reverso
    0.50
    writeField
    0.50
    Activations Density 26.504%

    No Known Activations