© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9752
    Prev
    Next
    INDEX
    Explanations

    pivot, columns, rows

    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
    يكل
    0.42
    or
    0.41
    Chk
    0.41
    å
    0.39
    arrant
    0.38
    сня
    0.37
    راك
    0.37
    astal
    0.37
    astopol
    0.37
    Codec
    0.37
    POSITIVE LOGITS
     deducting
    0.48
     née
    0.46
     tunt
    0.45
     worldRank
    0.44
    ⛲
    0.42
     ఇటీ
    0.41
     düş
    0.40
     `:`,
    0.40
    𝒕
    0.39
     Ayo
    0.39
    Activations Density 0.080%

    No Known Activations