© 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. 61395
    Prev
    Next
    INDEX
    Explanations

    lessening effects

    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
     a
    1.70
    。
    1.65
    ។
    1.38
    ların
    1.21
    1
    1.20
    c
    1.20
    리
    1.17
    ></
    1.16
    $.
    1.15
    Р
    1.15
    POSITIVE LOGITS
    in
    1.31
    то
    1.18
     vertebrae
    1.06
    ारा
    1.04
    ą
    1.04
    ರ್
    1.03
    ו
    1.03
     for
    1.02
    isasi
    1.02
    ర్
    1.01
    Activations Density 0.000%

    No Known Activations