© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129603
    Prev
    Next
    INDEX
    Explanations

    elegant process

    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_1_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
    2
    1.47
     was
    1.43
    u
    1.41
    i
    1.31
    the
    1.18
    на
    1.16
    いた
    1.15
    a
    1.13
    t
    1.12
     که
    1.09
    POSITIVE LOGITS
    لي
    1.13
    ็อก
    1.12
    л
    1.02
    .
    1.00
    দের
    0.98
    ти
    0.98
    什么
    0.94
    ла
    0.94
    ल
    0.93
    ล
    0.90
    Activations Density 0.000%

    No Known Activations