© 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. 75036
    Prev
    Next
    INDEX
    Explanations

    can/could get/find/think/ask/imagine/eat

    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
    ambah
    0.30
    ätzlich
    0.30
     eradicated
    0.29
     }}>
    0.29
    }}>
    0.29
    okovic
    0.29
    ]+/
    0.29
    此前
    0.29
     alleviated
    0.29
    是否
    0.28
    POSITIVE LOGITS
     ሂደት
    0.34
    inim
    0.32
     собстве
    0.31
     layman
    0.31
     nume
    0.31
     Fabi
    0.30
     cradle
    0.30
     Limb
    0.30
    beams
    0.30
     progen
    0.29
    Activations Density 0.003%

    No Known Activations