© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 120653
    Prev
    Next
    INDEX
    Explanations

    observable pipes subscribe

    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_38_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
    更新
    0.46
    jela
    0.41
     セット
    0.40
     settler
    0.39
     periodically
    0.38
     updates
    0.37
    Updating
    0.37
    𒌝
    0.37
     regularly
    0.36
     тог
    0.36
    POSITIVE LOGITS
     diversion
    0.44
    حافظ
    0.40
     chromed
    0.39
     Amman
    0.38
     oath
    0.37
    Rational
    0.37
    Float
    0.37
    Round
    0.37
     dirige
    0.37
     optimisation
    0.37
    Activations Density 0.001%

    No Known Activations