© 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. 134401
    Prev
    Next
    INDEX
    Explanations

    ideas

    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
    in
    2.20
    t
    1.76
    s
    1.64
    l
    1.61
    w
    1.38
    ,
    1.38
    v
    1.20
    S
    1.20
    "
    1.15
     in
    1.13
    POSITIVE LOGITS
    1
    1.34
    <0x80>
    1.05
    يل
    0.99
    ية
    0.98
     razão
    0.96
     فائد
    0.94
     legjobb
    0.94
    на
    0.93
    １
    0.93
     toliko
    0.92
    Activations Density 0.000%

    No Known Activations