© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180642
    Prev
    Next
    INDEX
    Explanations

    script tags url references

    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_24_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
     ষে
    0.44
    ன்னி
    0.43
    дым
    0.43
    蓯
    0.43
    дова
    0.42
     caregiver
    0.41
    тера
    0.40
     unset
    0.40
    ➽
    0.40
     Hens
    0.39
    POSITIVE LOGITS
    ST
    0.53
    COS
    0.45
     osa
    0.45
     carica
    0.45
     ufficiale
    0.45
    ज
    0.43
     לח
    0.43
    SError
    0.43
     digitale
    0.42
     চালাচ্ছে
    0.42
    Activations Density 0.000%

    No Known Activations