© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61649
    Prev
    Next
    INDEX
    Explanations

    wandering

    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_2_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
    리
    1.51
     as
    1.23
    した
    1.20
    ้
    1.12
    )!
    1.06
     be
    1.00
    ৮
    1.00
     letz
    0.95
     powied
    0.95
    리로
    0.95
    POSITIVE LOGITS
    in
    1.09
    ాలు
    1.02
    ט
    0.99
    ле
    0.96
    tes
    0.95
    tte
    0.94
    ll
    0.92
    tas
    0.92
    า
    0.91
    top
    0.89
    Activations Density 0.001%

    No Known Activations