© 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. 12321
    Prev
    Next
    INDEX
    Explanations

    Manolo Caracol

    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
     analisa
    0.52
     minyak
    0.51
     coltiv
    0.48
    ႉ
    0.47
     concentração
    0.47
    ጸ
    0.46
     pengukuran
    0.46
     caminar
    0.46
    ̚
    0.45
     menciptakan
    0.45
    POSITIVE LOGITS
    o
    0.56
    THERE
    0.50
    index
    0.47
    ート
    0.45
    an
    0.45
    }(\
    0.45
     चुने
    0.45
    s
    0.45
    observable
    0.44
    n
    0.43
    Activations Density 0.000%

    No Known Activations