© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54782
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     Ist
    0.38
    Ist
    0.37
    জ্ঞান
    0.37
    对外
    0.37
    ei
    0.36
    Ei
    0.36
    菱
    0.36
    EI
    0.36
     hu
    0.36
     Propositions
    0.36
    POSITIVE LOGITS
     sore
    0.49
     mic
    0.46
     nic
    0.45
     rule
    0.41
     regel
    0.40
    tyle
    0.40
    ure
    0.39
    rule
    0.38
     thước
    0.38
    柱
    0.38
    Activations Density 0.001%

    No Known Activations