© 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. 136524
    Prev
    Next
    INDEX
    Explanations

    SELECTION FORM GET

    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
    r
    0.59
    𝗋
    0.52
    ol
    0.51
     έν
    0.50
     tones
    0.49
     amps
    0.48
     smel
    0.48
     vies
    0.48
    ﺭ
    0.48
     R
    0.48
    POSITIVE LOGITS
    َی
    0.66
    symmetry
    0.61
    یکی
    0.57
    committee
    0.56
    ности
    0.54
    January
    0.53
    memory
    0.52
    polarity
    0.52
    GRAM
    0.52
    乱流
    0.52
    Activations Density 0.005%

    No Known Activations