© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215468
    Prev
    Next
    INDEX
    Explanations

    freedom of expression

    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_5_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
    te
    1.04
     Ό
    0.95
    ૧
    0.92
    körper
    0.91
    ে
    0.85
    াক্তন
    0.85
     ষে
    0.84
    tható
    0.84
    kke
    0.84
     Firestore
    0.84
    POSITIVE LOGITS
    is
    1.52
    ت
    1.30
    ان
    1.23
    the
    1.20
    ע
    1.20
    ט
    1.19
    ত
    1.16
    it
    1.16
     t
    1.15
    t
    1.12
    Activations Density 0.000%

    No Known Activations