© 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. 215601
    Prev
    Next
    INDEX
    Explanations

    seeing them

    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
     creatures
    0.34
    PROTOCOL
    0.33
    वरण
    0.32
     crews
    0.32
    ποιή
    0.31
    ESSAGE
    0.31
     Смо
    0.31
    {@
    0.31
    зу
    0.30
    phere
    0.30
    POSITIVE LOGITS
    reis
    0.42
     pale
    0.36
     avenida
    0.35
     approved
    0.35
     Carr
    0.35
     चालीस
    0.34
     ven
    0.34
     csak
    0.33
     केवल
    0.32
     reis
    0.32
    Activations Density 0.003%

    No Known Activations