© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205162
    Prev
    Next
    INDEX
    Explanations

    yum install

    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_6_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
    ;
    1.77
    א
    1.39
    ال
    1.36
    :
    1.35
    ه
    1.34
    in
    1.30
    ع
    1.26
    ad
    1.25
    ח
    1.24
    ir
    1.22
    POSITIVE LOGITS
    ၃
    0.93
     plików
    0.91
     વ્યવ
    0.86
    Sides
    0.86
    ции
    0.85
    și
    0.85
     પ્રકાશ
    0.84
    ስቃሴ
    0.84
    Gruß
    0.82
    mps
    0.80
    Activations Density 0.000%

    No Known Activations