© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64122
    Prev
    Next
    INDEX
    Explanations

    names

    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_46_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
     m
    2.69
     м
    1.98
     م
    1.89
    m
    1.56
    <0xA0>
    1.40
     म
    1.38
    ｍ
    1.35
    𝑚
    1.26
     ম
    1.20
     ம
    1.17
    POSITIVE LOGITS
     Mantel
    0.37
    िवेदी
    0.35
    amantha
    0.35
    혐
    0.34
     Teri
    0.34
     Tamar
    0.33
    缟
    0.33
    盪
    0.32
    rectionType
    0.32
     Ceci
    0.32
    Activations Density 0.026%

    No Known Activations