© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11264
    Prev
    Next
    INDEX
    Explanations

    words related to progress and optimization

    oai_token-act-pair · gemini-2.0-flash

    words indicating improvement or efficiency

    np_token-act-pair-logits · gpt-4o-mini

    improvements and results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     protoimpl
    -0.63
    AnchorStyles
    -0.53
     ModelExpression
    -0.53
     ambos
    -0.49
    нија
    -0.48
    Ambos
    -0.45
     الوطنيه
    -0.45
     couple
    -0.45
     зае
    -0.45
     Munic
    -0.45
    POSITIVE LOGITS
     appreciably
    0.66
     substantially
    0.65
     materially
    0.63
     significantly
    0.63
    AndEndTag
    0.61
     considerably
    0.61
     drastically
    0.58
     lenker
    0.57
     dramatically
    0.57
     значительно
    0.56
    Activations Density 9.414%

    No Known Activations