© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36155
    Prev
    Next
    INDEX
    Explanations

    arm

    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
    glightbox
    0.40
    胗
    0.37
    னீ
    0.36
     electrolysis
    0.36
     Tob
    0.36
     *}
    0.35
    嘞
    0.35
    建成
    0.35
    ެވެ
    0.35
     Abbe
    0.34
    POSITIVE LOGITS
    Arm
    2.69
     arm
    2.63
     ARM
    2.58
     Arm
    2.53
    ARM
    2.52
    arm
    2.42
     arms
    2.33
     Arms
    2.17
    arms
    2.14
    Arms
    2.13
    Activations Density 0.144%

    No Known Activations