© 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. 11863
    Prev
    Next
    INDEX
    Explanations

    marketing language for loans

    oai_token-act-pair · gemini-2.0-flash

    Business applications advertisements

    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
    SupportActionBar
    -0.60
    CodeAttribute
    -0.59
    .}(
    -0.55
     $
    -0.54
    matchCondition
    -0.53
    }{$
    -0.53
    AndroidJUnit
    -0.52
     &\
    -0.49
     TextAppearance
    -0.48
     $\$
    -0.47
    POSITIVE LOGITS
    parsedMessage
    0.51
     informée
    0.51
    InnerText
    0.50
     Rent
    0.49
    Климат
    0.48
     cabina
    0.47
    jmniej
    0.47
    ⓘ
    0.46
    RetentionPolicy
    0.46
    MarshalTo
    0.45
    Activations Density 7.574%

    No Known Activations