© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61671
    Prev
    Next
    INDEX
    Explanations

    error messages

    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_11_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
    t
    0.82
    ن
    0.71
    ت
    0.68
    н
    0.65
    import
    0.63
    is
    0.60
    n
    0.60
    т
    0.60
    ار
    0.59
    س
    0.58
    POSITIVE LOGITS
     образу
    0.59
     l
    0.58
    zący
    0.57
    OR
    0.53
     baseless
    0.51
     अव
    0.50
     ఫ
    0.50
     \
    0.50
    َان
    0.50
     unwilling
    0.49
    Activations Density 0.003%

    No Known Activations