© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88575
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by closing punctuation

    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_23_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
    hers
    0.40
    Þ
    0.36
    D
    0.35
    ライ
    0.34
    des
    0.34
     گیا
    0.34
    HUB
    0.34
    カ
    0.33
    Hub
    0.32
     hears
    0.32
    POSITIVE LOGITS
    ዣ
    0.43
    ementara
    0.40
     fxaa
    0.40
    молу
    0.40
    седнев
    0.39
    傛
    0.39
     spaceleft
    0.38
     уйнарга
    0.38
    ியும்
    0.38
    pieceSelection
    0.38
    Activations Density 0.005%

    No Known Activations