© 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. 8960
    Prev
    Next
    INDEX
    Explanations

    mentions of drinking, especially heavy drinking.

    oai_token-act-pair · gemini-2.0-flash

    heavy

    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
     heavy
    -3.22
     Heavy
    -3.11
    Heavy
    -3.09
    heavy
    -2.95
     HEAVY
    -2.83
     heavier
    -2.48
     heaviest
    -2.45
     pesado
    -1.87
     heav
    -1.81
     pesada
    -1.77
    POSITIVE LOGITS
    sidemargin
    0.59
    Edm
    0.50
    CreateModel
    0.48
    inys
    0.47
    werks
    0.47
     Milner
    0.46
    CopyWith
    0.44
     Puntos
    0.44
    duire
    0.44
    fhir
    0.43
    Activations Density 2.311%

    No Known Activations