© 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. 216508
    Prev
    Next
    INDEX
    Explanations

    God, Israel, creator, Gustavo

    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
    lois
    0.39
    ಬ
    0.39
    ब्रु
    0.38
    aithe
    0.37
    obranch
    0.37
    /';
    0.36
    "><
    0.36
    褴
    0.36
    tric
    0.36
    ར
    0.35
    POSITIVE LOGITS
     اسرائیل
    0.42
     Israel
    0.41
     SHALL
    0.41
     Judah
    0.40
    礬
    0.40
     IAA
    0.40
    SEL
    0.40
     avenge
    0.39
     sensation
    0.39
     RPA
    0.38
    Activations Density 0.000%

    No Known Activations