© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52634
    Prev
    Next
    INDEX
    Explanations

    from ' or " or @

    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
    azza
    0.44
    Bard
    0.41
     wur
    0.39
     Bard
    0.39
    ATR
    0.39
    所需
    0.38
    援
    0.37
    如果要
    0.36
     پست
    0.36
    kcal
    0.35
    POSITIVE LOGITS
     Allow
    0.42
     regulator
    0.38
     обе
    0.37
     रोकना
    0.37
    წ
    0.37
     regulators
    0.37
    拾
    0.37
     Honestly
    0.36
     கும
    0.36
     showering
    0.35
    Activations Density 0.000%

    No Known Activations