Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260618
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ات
    1.69
    orice
    1.31
     того
    1.22
    osy
    1.20
    jí
    1.17
    osar
    1.15
    eniem
    1.15
    s
    1.14
    os
    1.14
    am
    1.11
    POSITIVE LOGITS
     effectuées
    1.20
     अर्जित
    1.16
    豈
    1.16
     possibilités
    1.16
     Revisited
    1.14
     incipient
    1.14
     presumption
    1.14
    ⤥
    1.14
     évident
    1.13
     Hopefully
    1.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.