© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76293
    Prev
    Next
    INDEX
    Explanations

    spell correction and error distance

    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_31_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
    otha
    0.40
    宣
    0.39
     Ush
    0.38
     Jor
    0.38
    ontal
    0.38
     Sexuality
    0.38
     crank
    0.37
     parameterType
    0.37
     Hydraul
    0.36
    鈾
    0.36
    POSITIVE LOGITS
    Tray
    0.38
     Samo
    0.37
    Activities
    0.36
    compar
    0.35
     repair
    0.35
    indications
    0.35
     remediation
    0.35
    enov
    0.35
    Repair
    0.35
    Rm
    0.35
    Activations Density 0.054%

    No Known Activations