© 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. 14539
    Prev
    Next
    INDEX
    Explanations

    colons and other punctuation followed by words related to various categories of entertainment and events

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     emplois
    -0.64
    SharedCtor
    -0.63
    ГЛА
    -0.61
    TagMode
    -0.61
    ьаж
    -0.60
    principalTable
    -0.59
    anmoins
    -0.57
    UnknownFieldSet
    -0.56
     vertus
    -0.55
    avyzd
    -0.55
    POSITIVE LOGITS
    styleUrls
    0.62
     незавершена
    0.53
     Η
    0.52
    Activité
    0.52
    SuccessListener
    0.50
    Το
    0.48
    ioutil
    0.47
    ρέ
    0.47
    Οι
    0.47
    RUnlock
    0.46
    Activations Density 23.712%

    No Known Activations