© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3484
    Prev
    Next
    INDEX
    Explanations

    words suggesting novelty or location

    oai_token-act-pair · gemini-2.0-flash

    part/parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     متعلقه
    -0.89
    mybatisplus
    -0.78
     ſeveral
    -0.75
     Efq
    -0.72
     ſmall
    -0.71
     Diſ
    -0.69
    DoubleQuotes
    -0.69
    erweise
    -0.69
     المعيارى
    -0.68
    NewRow
    -0.67
    POSITIVE LOGITS
     part
    2.25
     parts
    2.23
    part
    2.09
    Part
    2.00
    parts
    1.94
     Parts
    1.88
    Parts
    1.87
     Part
    1.84
     PARTS
    1.69
     parte
    1.58
    Activations Density 2.756%

    No Known Activations