© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20713
    Prev
    Next
    INDEX
    Explanations

    safe

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     straightforward
    0.47
    或
    0.46
     smooth
    0.46
     easy
    0.45
     elegant
    0.44
     flawless
    0.42
     inexplicable
    0.41
     healthier
    0.41
     beautiful
    0.40
     healthy
    0.40
    POSITIVE LOGITS
     an
    0.59
     -,
    0.53
    -,
    0.50
     وم
    0.50
    _,
    0.45
     –,
    0.45
     agus
    0.42
     、,
    0.42
    آن
    0.41
    $-,
    0.41
    Activations Density 0.028%

    No Known Activations