© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253348
    Prev
    Next
    INDEX
    Explanations

    murm

    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_56_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
    าม
    0.43
    ีก
    0.37
    Sig
    0.37
    Pued
    0.37
    Nub
    0.37
    纸
    0.37
     .{
    0.36
    ষ্টিত
    0.36
    旯
    0.36
    Irr
    0.36
    POSITIVE LOGITS
     mur
    0.86
     MUR
    0.76
    mur
    0.73
     Mur
    0.72
    MUR
    0.71
    Mur
    0.67
     Murat
    0.63
     Murakami
    0.62
     muri
    0.53
     मुर
    0.52
    Activations Density 0.000%

    No Known Activations