© 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. 6092
    Prev
    Next
    INDEX
    Explanations

    Spanish words and references to Javascript and coding

    oai_token-act-pair · gemini-2.0-flash

    Multiple programming languages

    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
    ::_('
    -0.60
     فريبيس
    -0.47
     تانيه
    -0.47
    MeasureSpec
    -0.47
    gadier
    -0.47
    __":
    -0.46
     omnium
    -0.45
    __':
    -0.44
    RectangleBorder
    -0.44
     مرئيه
    -0.44
    POSITIVE LOGITS
     perdidos
    0.64
     betweenstory
    0.59
    kloped
    0.59
    Переваги
    0.59
     réglable
    0.59
    liceerd
    0.56
     positivas
    0.56
     unconscious
    0.55
     Exacts
    0.55
    LookAnd
    0.55
    Activations Density 0.273%

    No Known Activations