© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4189
    Prev
    Next
    INDEX
    Explanations

    a variety of words, without an obvious relationship.

    oai_token-act-pair · gemini-2.0-flash

    Approach

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    帖最后由
    -0.66
    AnchorStyles
    -0.65
     الرياضيه
    -0.62
    rrggbb
    -0.60
     تضيفلها
    -0.59
    出版年
    -0.59
    WithIOException
    -0.57
    ArgsConstructor
    -0.57
     onItemClick
    -0.56
     doigt
    -0.54
    POSITIVE LOGITS
     approach
    1.18
     approached
    1.16
    approach
    1.13
     Approach
    1.06
     approaches
    1.05
     APPROACH
    1.04
    Approach
    0.99
     approaching
    0.89
     Approaches
    0.84
    appro
    0.82
    Activations Density 3.596%

    No Known Activations