© 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. 8062
    Prev
    Next
    INDEX
    Explanations

    phrases about complex questions and uncertainties

    oai_token-act-pair · gemini-2.0-flash

    question, point

    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
     aient
    -0.47
     extérieures
    -0.47
     snart
    -0.44
    ifter
    -0.44
     kelompok
    -0.42
    We
    -0.42
     actuelles
    -0.42
     Añade
    -0.41
     élevées
    -0.41
     aggiungere
    -0.40
    POSITIVE LOGITS
     ModelExpression
    1.11
    jspx
    0.85
     ujednoznacz
    0.80
    VersionUID
    0.80
    awtextra
    0.78
    المشاركات
    0.75
     protoimpl
    0.75
     beginnetje
    0.74
     HasFactory
    0.74
    parsedMessage
    0.73
    Activations Density 24.789%

    No Known Activations