© 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. 84997
    Prev
    Next
    INDEX
    Explanations

    words and phrases after certain words

    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
     glee
    0.43
     goof
    0.43
     colectivo
    0.42
    땡
    0.42
     papá
    0.41
     '
    0.40
     colet
    0.40
     cab
    0.40
     wacky
    0.40
     nasty
    0.39
    POSITIVE LOGITS
    第壹百
    0.46
    Aid
    0.42
     października
    0.41
    Fro
    0.40
     सक्छ
    0.40
     січня
    0.39
    してきました
    0.37
    icrosoft
    0.37
     未来
    0.37
    ܂
    0.37
    Activations Density 0.061%

    No Known Activations