© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43201
    Prev
    Next
    INDEX
    Explanations

    pine fixtures

    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
    ۔
    0.67
     הראש
    0.66
    कांड
    0.65
    िंग
    0.65
    in
    0.64
    have
    0.64
    he
    0.63
    us
    0.61
    த்தில்
    0.61
    ita
    0.61
    POSITIVE LOGITS
    ش
    0.82
     Dezember
    0.61
    </h4>
    0.57
    ש
    0.57
    ни
    0.56
    })$
    0.55
    ,"
    0.55
     Ni
    0.54
     mô
    0.53
    <0x91>
    0.52
    Activations Density 0.010%

    No Known Activations