© 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. 103729
    Prev
    Next
    INDEX
    Explanations

    tree bark

    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
     on
    1.26
     It
    0.92
    list
    0.92
     to
    0.91
    л
    0.90
    schol
    0.86
    to
    0.85
    nitro
    0.85
    manager
    0.83
    nig
    0.80
    POSITIVE LOGITS
    ;
    1.60
    :
    1.36
    ,
    1.26
    -
    1.26
    a
    1.25
    /
    1.20
    ला
    1.14
    ك
    1.14
    ai
    1.12
    ).
    0.98
    Activations Density 0.002%

    No Known Activations