© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79323
    Prev
    Next
    INDEX
    Explanations

    basic followed by descriptors

    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_0_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
    ur
    1.87
    i
    1.48
    ado
    1.39
    kan
    1.39
    res
    1.31
    ார்
    1.31
    ido
    1.30
    بر
    1.27
    ized
    1.26
    naire
    1.25
    POSITIVE LOGITS
    ש
    1.98
    고
    1.61
    ۹
    1.61
    ת
    1.59
    يد
    1.39
    }
    1.38
     convene
    1.34
     consegu
    1.34
    ’
    1.34
    ৪
    1.33
    Activations Density 0.007%

    No Known Activations