© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39170
    Prev
    Next
    INDEX
    Explanations

    syn, synth, health

    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_3_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
    '
    0.83
    t
    0.77
    ’
    0.76
     symmetry
    0.73
     machinery
    0.71
    et
    0.69
    o
    0.66
     in
    0.65
     intros
    0.64
     strikes
    0.64
    POSITIVE LOGITS
    ية
    0.72
    ش
    0.68
    ال
    0.66
    4
    0.66
    ческой
    0.65
    كيل
    0.65
    8
    0.65
    До
    0.64
    انس
    0.64
    3
    0.63
    Activations Density 0.000%

    No Known Activations