© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69768
    Prev
    Next
    INDEX
    Explanations

    Ed25519 keys

    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_51_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
    ag
    0.43
     tamper
    0.41
    Wait
    0.40
    Ꭵ
    0.39
    垣
    0.38
     Lowell
    0.38
    лера
    0.37
    warte
    0.37
    वर्त
    0.37
     tam
    0.36
    POSITIVE LOGITS
    Bio
    0.39
    دار
    0.39
     TextField
    0.39
     Nxh
    0.38
    łość
    0.37
    酘
    0.37
    앉
    0.37
     Bahadur
    0.37
    DarkMode
    0.36
     wor
    0.36
    Activations Density 0.000%

    No Known Activations