© 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. 79952
    Prev
    Next
    INDEX
    Explanations

    on

    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
    ذه
    0.40
     Blu
    0.39
    غ
    0.38
    ्रु
    0.35
    تمع
    0.35
     Grants
    0.35
    日
    0.35
     Bled
    0.34
    流
    0.34
    club
    0.34
    POSITIVE LOGITS
    UserName
    0.43
    يں
    0.42
     braid
    0.40
     sắp
    0.40
     WindowStateType
    0.38
    Strafpunkte
    0.38
     Wochschr
    0.38
    㕕
    0.38
     trống
    0.37
     যশোরের
    0.37
    Activations Density 0.001%

    No Known Activations