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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261068
    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
    て
    1.24
    edin
    1.16
    hhhh
    1.16
    та
    1.12
     chắc
    1.06
    рас
    1.05
     cas
    0.99
    ль
    0.98
    {\
    0.98
    х
    0.98
    POSITIVE LOGITS
    ÑA
    1.23
     Issues
    1.22
     ощущения
    1.22
    an
    1.21
    WTO
    1.20
     अभिगमन
    1.20
     Prosecution
    1.20
     exclusivity
    1.19
     हिमा
    1.18
     attribution
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.