© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36501
    Prev
    Next
    INDEX
    Explanations

    spaceX rocket Falcon 9

    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
    Y
    0.89
    S
    0.87
    an
    0.80
    T
    0.74
    ag
    0.70
    K
    0.70
    ac
    0.70
    cle
    0.70
    formed
    0.70
    alpine
    0.69
    POSITIVE LOGITS
    ן
    0.95
    ี
    0.87
    ת
    0.80
    س
    0.75
    ד
    0.72
    ิน
    0.70
    ில்
    0.70
    র
    0.69
    า
    0.69
    ం
    0.68
    Activations Density 0.001%

    No Known Activations