© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179492
    Prev
    Next
    INDEX
    Explanations

    form input labels

    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_24_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
     അടി
    0.40
    чне
    0.38
     uner
    0.38
     ғ
    0.38
    場で
    0.37
     وړ
    0.37
     alongside
    0.36
     அடி
    0.36
    لوان
    0.36
    손
    0.35
    POSITIVE LOGITS
    ahua
    0.45
    ency
    0.43
    amesh
    0.42
    endo
    0.42
    iat
    0.41
    แต่ง
    0.40
    ércio
    0.39
    emia
    0.39
    ekten
    0.39
    arend
    0.39
    Activations Density 0.001%

    No Known Activations