© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11849
    Prev
    Next
    INDEX
    Explanations

    complex chemical names and formulas.

    oai_token-act-pair · gemini-2.0-flash

    Chemical components

    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
    ########.
    -0.91
     سكانية
    -0.84
     Infórmanos
    -0.81
    цездатний
    -0.81
     ErrIntOverflow
    -0.75
    __":
    
    -0.75
     समीक्षाएं
    -0.74
     betweenstory
    -0.73
    Personensuche
    -0.73
     ModelExpression
    -0.69
    POSITIVE LOGITS
    dimethy
    0.68
    Dibrom
    0.63
    pheny
    0.62
    pyrid
    0.62
    benz
    0.61
    furan
    0.60
    propy
    0.60
    propane
    0.59
    hexane
    0.58
    Tetrach
    0.58
    Activations Density 14.721%

    No Known Activations