© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104567
    Prev
    Next
    INDEX
    Explanations

    did

    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_1_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
    ir
    1.80
    or
    1.64
     He
    1.53
     aujourd
    1.50
    viii
    1.48
    ור
    1.48
    s
    1.45
    ۴
    1.44
    in
    1.43
    ين
    1.43
    POSITIVE LOGITS
    lords
    0.91
    },
    0.89
    I
    0.87
    bildung
    0.86
    ㈣
    0.82
    Utils
    0.79
    ?
    0.79
    da
    0.78
    lains
    0.78
    line
    0.76
    Activations Density 0.001%

    No Known Activations