© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122478
    Prev
    Next
    INDEX
    Explanations

    dont wait then act

    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_37_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
     utilising
    0.44
     utilizing
    0.41
    wci
    0.40
    ≋
    0.39
     ludicrous
    0.39
     sprzę
    0.39
     utilizando
    0.38
     vosotros
    0.38
     utilises
    0.38
    wał
    0.38
    POSITIVE LOGITS
     bound
    0.42
     Bound
    0.38
    Et
    0.37
    中小
    0.36
     но
    0.36
     ши
    0.36
     S
    0.35
     qua
    0.35
     sido
    0.35
     Initialization
    0.35
    Activations Density 0.000%

    No Known Activations