© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215036
    Prev
    Next
    INDEX
    Explanations

    blindfolding

    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_5_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
    ਰ
    1.27
    '
    1.15
     daqu
    1.09
    ർ
    1.06
    up
    1.05
    зыва
    0.98
    ступа
    0.98
     ayaa
    0.97
     nuova
    0.96
     όχι
    0.96
    POSITIVE LOGITS
    d
    1.75
    t
    1.67
    א
    1.51
    s
    1.37
    b
    1.36
    g
    1.23
    د
    1.23
    c
    1.21
    ان
    1.13
    f
    1.09
    Activations Density 0.000%

    No Known Activations