© 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. 214324
    Prev
    Next
    INDEX
    Explanations

    versus

    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
    Ꮪ
    0.47
    ｓ
    0.46
    radius
    0.45
    rs
    0.45
    shad
    0.42
    שׁ
    0.40
    স
    0.40
    seven
    0.39
     radius
    0.39
     TA
    0.39
    POSITIVE LOGITS
    ত্রের
    0.38
    ）.
    0.38
     înainte
    0.37
    irtschaft
    0.35
     poté
    0.34
    PPT
    0.34
    োন
    0.34
    ：（
    0.34
    :'
    0.33
    ]),
    0.33
    Activations Density 0.000%

    No Known Activations