© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110510
    Prev
    Next
    INDEX
    Explanations

    ika portion

    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_2_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
    ０
    1.06
    0
    1.05
     avocat
    1.04
    ING
    1.02
    ik
    0.98
    υτό
    0.98
     adicionar
    0.95
    логи
    0.95
    возможно
    0.95
    ur
    0.94
    POSITIVE LOGITS
    し
    1.30
    ä
    1.16
    ться
    1.09
    ৫
    1.05
    ем
    1.02
    وم
    1.00
     the
    0.98
    ї
    0.97
    う
    0.96
    ii
    0.95
    Activations Density 0.000%

    No Known Activations