© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89244
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings and ids

    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_23_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
     ليك
    0.34
    至
    0.33
    切り
    0.32
    РИ
    0.31
    Crime
    0.31
    }$&$-
    0.30
     HCI
    0.30
     crime
    0.29
     poner
    0.29
    竊
    0.29
    POSITIVE LOGITS
    钊
    0.34
     oppervlak
    0.32
    భ్య
    0.32
    ojen
    0.32
    iada
    0.31
    otion
    0.31
    iology
    0.31
    mana
    0.31
     των
    0.30
    ccia
    0.30
    Activations Density 0.000%

    No Known Activations