© 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. 12251
    Prev
    Next
    INDEX
    Explanations

    language about an artistic or technical method of visually breaking things down into components

    oai_token-act-pair · gemini-2.0-flash

    Visual arts

    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
    الحياه
    -0.58
     defStyleAttr
    -0.46
    naux
    -0.46
    áře
    -0.45
    addContainerGap
    -0.44
    userdetails
    -0.44
    anah
    -0.43
    shadow
    -0.43
     Wikimedijinoj
    -0.43
    listi
    -0.42
    POSITIVE LOGITS
    DBNull
    0.71
     GenerationType
    0.70
    queryInterface
    0.65
    Coordenadas
    0.62
    ⓧ
    0.60
    LayoutConstraint
    0.59
     Réponses
    0.59
     Wicidata
    0.58
    Personendaten
    0.56
    bkz
    0.55
    Activations Density 9.116%

    No Known Activations