© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132419
    Prev
    Next
    INDEX
    Explanations

    A- prefix

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ње
    0.45
    ньо
    0.45
    :@
    0.38
    庵
    0.37
     Discourse
    0.37
     দেহ
    0.36
     vesc
    0.36
     Bishop
    0.36
     discourse
    0.36
    opian
    0.35
    POSITIVE LOGITS
    Us
    0.40
    ayu
    0.40
    Wu
    0.39
    虺
    0.38
    ma
    0.36
    ല്ലാത്ത
    0.35
    stant
    0.35
    ayment
    0.35
    dU
    0.35
     डब्ल्यू
    0.35
    Activations Density 0.000%

    No Known Activations