© 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. 164249
    Prev
    Next
    INDEX
    Explanations

    among us, uncle, away from

    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
    涪
    0.61
    ्हा
    0.59
    疃
    0.56
    リン
    0.55
    橐
    0.55
    าค
    0.54
    㣩
    0.52
    ikti
    0.52
    ُر
    0.51
    OCE
    0.51
    POSITIVE LOGITS
    тися
    0.57
    c
    0.55
    x
    0.52
    ced
    0.51
    inkle
    0.51
    trs
    0.51
    cid
    0.50
    quela
    0.50
    acing
    0.50
    țe
    0.50
    Activations Density 0.000%

    No Known Activations