© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24061
    Prev
    Next
    INDEX
    Explanations

    ://

    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_56_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
     rectification
    0.41
     आर्टिफिशियल
    0.40
     Basement
    0.40
     /
    0.39
    MenuList
    0.39
    composable
    0.38
     compos
    0.38
    PAINT
    0.37
     Баскетбол
    0.37
     retained
    0.37
    POSITIVE LOGITS
     “
    0.42
     sle
    0.38
    olk
    0.38
     tamar
    0.37
     SCGS
    0.36
    ױ
    0.36
    タウン
    0.36
     ”
    0.36
     seab
    0.34
     estr
    0.34
    Activations Density 0.001%

    No Known Activations