© 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. 12158
    Prev
    Next
    INDEX
    Explanations

    emphatic descriptions using the word "far."

    oai_token-act-pair · gemini-2.0-flash

    far

    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
     مرئيه
    -0.67
     typelib
    -0.65
    Autoritní
    -0.53
     Signalez
    -0.53
    EndGlobalSection
    -0.51
     мәкал
    -0.50
    ValueStyle
    -0.48
    WireFormatLite
    -0.47
     يتيمه
    -0.44
    InjectAttribute
    -0.43
    POSITIVE LOGITS
     becauſe
    0.72
     Baillar
    0.71
     Majefty
    0.69
     myſelf
    0.68
     ejus
    0.66
     Monfieur
    0.63
     himſelf
    0.63
     quæ
    0.62
     itſelf
    0.61
     Cæsar
    0.60
    Activations Density 7.445%

    No Known Activations