© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4129
    Prev
    Next
    INDEX
    Explanations

    broad categories, but is primarily focused on specific types of adjectives.

    oai_token-act-pair · gemini-2.0-flash

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    SharedDtor
    -0.54
     насељу
    -0.50
     كومونز
    -0.49
    )__
    -0.49
    PropertyChanged
    -0.48
    __((
    -0.48
    Voci
    -0.48
    principalColumn
    -0.47
    %
    -0.47
    aduras
    -0.46
    POSITIVE LOGITS
    RetentionPolicy
    0.63
    存于互联网档案馆
    0.56
     lockers
    0.53
     ویکی‌پدیای
    0.52
    ьаж
    0.52
    capulco
    0.51
     playgrounds
    0.51
     playground
    0.50
     bottle
    0.50
     ski
    0.49
    Activations Density 2.021%

    No Known Activations