© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43389
    Prev
    Next
    INDEX
    Explanations

    AutoTokenizer, AutoModel

    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
     fold
    0.23
     utilization
    0.23
     lawful
    0.22
     }}{
    0.22
     VALID
    0.22
     Akash
    0.22
    綰
    0.22
    }}}{
    0.21
     इतर
    0.21
    デート
    0.21
    POSITIVE LOGITS
     corto
    0.26
    ம்பரிய
    0.23
     pratica
    0.22
    frontier
    0.22
     práctica
    0.22
    ⌒
    0.22
    ósfera
    0.22
     practicar
    0.22
     prática
    0.21
    thren
    0.21
    Activations Density 0.003%

    No Known Activations