© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54026
    Prev
    Next
    INDEX
    Explanations

    determine if whether

    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_30_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
    వైపు
    0.46
    ্ী
    0.43
    เลต
    0.41
    宒
    0.40
     ખ્ર
    0.39
     forecasts
    0.38
     Commentaires
    0.38
    Liver
    0.38
    かせ
    0.38
    數量
    0.38
    POSITIVE LOGITS
    ^(
    0.37
    ](
    0.36
    gram
    0.36
    jabi
    0.36
    rab
    0.36
    led
    0.36
     Rab
    0.35
    象棋
    0.35
     არის
    0.35
     uv
    0.35
    Activations Density 0.002%

    No Known Activations