© 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. 155970
    Prev
    Next
    INDEX
    Explanations

    parts

    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
    বের
    0.43
    ในสนาม
    0.38
    ্টা
    0.37
    廚
    0.36
    ുകൾ
    0.35
    য়েক
    0.35
    キッチン
    0.35
    털
    0.35
     NavigationView
    0.35
    ரீ
    0.34
    POSITIVE LOGITS
     Carm
    0.42
    Dv
    0.39
    dv
    0.38
    Carm
    0.38
    dg
    0.38
    omechanics
    0.38
    zcz
    0.38
    Inv
    0.37
     Inv
    0.37
    සු
    0.37
    Activations Density 0.001%

    No Known Activations