© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76030
    Prev
    Next
    INDEX
    Explanations

    rating, risk level, vibe check

    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_31_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
    ্বল
    0.41
     threefold
    0.38
    䚲
    0.37
    纷
    0.37
    三种
    0.36
    треб
    0.36
    伦
    0.35
    itaires
    0.34
    resting
    0.34
    덟
    0.34
    POSITIVE LOGITS
    leder
    0.38
     migrant
    0.35
     AAU
    0.34
    ()}')
    0.34
     ACE
    0.34
     ဟ
    0.33
     ร้อย
    0.33
    meh
    0.32
     প
    0.32
    sø
    0.32
    Activations Density 0.044%

    No Known Activations