© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78575
    Prev
    Next
    INDEX
    Explanations

    (€

    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_53_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
     Θ
    0.37
    اقه
    0.36
     χ
    0.36
     shave
    0.36
     সংগ্রামী
    0.36
     barber
    0.35
    α
    0.35
    اق
    0.35
     Barber
    0.35
     ביותר
    0.35
    POSITIVE LOGITS
     $=$
    0.54
     $\}$
    0.54
     $($
    0.53
     $\{$
    0.53
     $\
    0.53
     $(-
    0.53
    ゚
    0.51
     $=\
    0.49
     $>$
    0.49
     $(\
    0.47
    Activations Density 0.003%

    No Known Activations