© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258441
    Prev
    Next
    INDEX
    Explanations

    Model Specific Registers

    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_22_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
    itudini
    0.48
    Vintage
    0.46
    This
    0.44
    Retail
    0.44
    Saludos
    0.44
     debit
    0.44
     modi
    0.43
    짠
    0.43
    Dial
    0.43
     supper
    0.43
    POSITIVE LOGITS
     LR
    0.48
     LAR
    0.44
    ⁡</
    0.44
    ငယ်
    0.43
     طلاب
    0.43
     لر
    0.43
     STATISTICS
    0.42
     लवकर
    0.42
     MOB
    0.42
    컥
    0.42
    Activations Density 0.000%

    No Known Activations