© 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. 133974
    Prev
    Next
    INDEX
    Explanations

    street address

    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
    лся
    0.95
     imao
    0.93
    ы
    0.90
    €™
    0.85
     اسرائی
    0.84
    스는
    0.84
     avaient
    0.82
    ார்
    0.80
     était
    0.80
     effectuées
    0.77
    POSITIVE LOGITS
    r
    1.23
    l
    1.08
    u
    1.08
    k
    1.04
    j
    0.96
    ir
    0.93
    i
    0.92
    g
    0.87
    gium
    0.84
    و
    0.83
    Activations Density 0.000%

    No Known Activations