© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14169
    Prev
    Next
    INDEX
    Explanations

    words related to measurements, positions, relations, and containing the letters "hold".

    oai_token-act-pair · gemini-2.0-flash

    hold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     held
    -1.34
    held
    -1.31
     hold
    -1.29
     Hold
    -1.26
     holding
    -1.20
     holds
    -1.20
    Hold
    -1.18
    Holding
    -1.16
     HOLD
    -1.16
    holds
    -1.16
    POSITIVE LOGITS
    /*
    0.58
     ModelExpression
    0.56
    appé
    0.55
     Palin
    0.55
    ########.
    0.54
     Италијани
    0.54
     poveznice
    0.54
     beet
    0.53
     retreating
    0.52
     Machiavelli
    0.52
    Activations Density 13.696%

    No Known Activations