© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42317
    Prev
    Next
    INDEX
    Explanations

    Google Opinion Rewards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    It
    0.61
    Their
    0.61
    Its
    0.60
    𝗠
    0.59
    itons
    0.58
    Upgradeable
    0.58
    Ⲩ
    0.57
     It
    0.56
    They
    0.55
    Ｍ
    0.55
    POSITIVE LOGITS
    ться
    0.98
    ,
    0.92
    ма
    0.78
     scolaire
    0.71
     opinion
    0.71
     problemi
    0.71
     spettac
    0.71
     fijo
    0.70
     regretted
    0.69
    р
    0.69
    Activations Density 0.001%

    No Known Activations