© 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. 162004
    Prev
    Next
    INDEX
    Explanations

    key-value assignment

    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
     wynosi
    0.30
    每
    0.29
     नवा
    0.29
    addition
    0.28
    ১১
    0.28
     selalu
    0.28
    тисти
    0.28
    扩大
    0.28
    novo
    0.27
    Укупно
    0.27
    POSITIVE LOGITS
     Bibel
    0.31
    روں
    0.28
     prophecy
    0.27
    быз
    0.27
    غو
    0.27
    }_{-}\
    0.26
    ゥム
    0.26
     ँ
    0.26
     ł
    0.25
     ruler
    0.25
    Activations Density 0.004%

    No Known Activations