© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91318
    Prev
    Next
    INDEX
    Explanations

    chipotle aioli, chipotle peppers, chicken noodle soup, Redfield

    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_3_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
    ي
    1.04
    י
    0.79
    ه
    0.79
    iunea
    0.72
    i
    0.72
     были
    0.70
    ния
    0.69
    ין
    0.64
     называ
    0.62
    h
    0.61
    POSITIVE LOGITS
    AL
    0.66
    F
    0.64
    AN
    0.64
    LLY
    0.63
    ens
    0.62
    ay
    0.59
    BK
    0.59
    ale
    0.58
    LC
    0.57
    BB
    0.57
    Activations Density 0.000%

    No Known Activations