© 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. 43625
    Prev
    Next
    INDEX
    Explanations

    in a place / context

    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
     BufferedReader
    0.23
     Вер
    0.20
    ОО
    0.19
    पह
    0.18
    ப்பிய
    0.18
     korero
    0.18
    𐰆
    0.18
    ные
    0.18
     ماده
    0.18
     ಕಾರ್ಯ
    0.18
    POSITIVE LOGITS
    sen
    0.23
    ren
    0.22
    ns
    0.22
     peux
    0.20
    tts
    0.20
    et
    0.20
    mming
    0.20
    h
    0.20
    na
    0.20
     exquis
    0.20
    Activations Density 0.007%

    No Known Activations