© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136913
    Prev
    Next
    INDEX
    Explanations

    hungry stomach growl

    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_12_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
    »)
    0.53
    袜
    0.50
    》。
    0.47
     पैकिंग
    0.46
    客
    0.45
     बीमा
    0.44
     ग्राफ
    0.44
    popularity
    0.44
    rief
    0.44
    ຊ
    0.43
    POSITIVE LOGITS
    urato
    0.54
    }">
    0.51
    olato
    0.50
    ната
    0.48
    atlan
    0.48
    eliz
    0.47
     slate
    0.47
    াতেই
    0.46
     Moderne
    0.46
     FGD
    0.46
    Activations Density 0.001%

    No Known Activations