© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12846
    Prev
    Next
    INDEX
    Explanations

    right speech, action, livelihood

    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_13_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
     PLANT
    0.45
    END
    0.45
    PROTO
    0.42
     END
    0.42
     JG
    0.42
    クリ
    0.41
    缫
    0.40
    AGO
    0.40
     obiettivo
    0.40
     STORY
    0.39
    POSITIVE LOGITS
     gören
    0.45
    ،
    0.45
     μας
    0.43
    hão
    0.42
    ́s
    0.42
    ed
    0.40
    existent
    0.40
    ocurrencies
    0.40
    ়
    0.40
    த்தில்
    0.40
    Activations Density 0.034%

    No Known Activations