© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27875
    Prev
    Next
    INDEX
    Explanations

    types

    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_40_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
    avgsalary
    0.41
    சாலை
    0.40
    তীর্থ
    0.40
    <unused86>
    0.40
    <unused50>
    0.39
    䧉
    0.39
    楂
    0.38
    詃
    0.37
    ämm
    0.37
    㻁
    0.37
    POSITIVE LOGITS
    Experts
    0.39
    蔥
    0.38
     opinions
    0.38
    ೊಂದ
    0.38
     modes
    0.38
     Mo
    0.37
    TIT
    0.36
     Experts
    0.36
    心
    0.36
     ret
    0.35
    Activations Density 0.000%

    No Known Activations