© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133695
    Prev
    Next
    INDEX
    Explanations

    in this

    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_6_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
    ing
    1.01
    ed
    0.92
    ة
    0.89
    ong
    0.87
    ↵
    0.80
    er
    0.79
    he
    0.79
    ak
    0.79
    og
    0.79
    ag
    0.76
    POSITIVE LOGITS
    "
    1.02
     mosques
    0.96
    ש
    0.92
    ’।
    0.89
    ам
    0.85
     agonists
    0.85
    ITAL
    0.84
    ల
    0.84
    ENSION
    0.83
    ।
    0.79
    Activations Density 0.009%

    No Known Activations