© 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. 170593
    Prev
    Next
    INDEX
    Explanations

    say ","

    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
     /*
    0.46
     /**@
    0.42
    ond
    0.42
     ?:
    0.41
     चिह्न
    0.39
    /*
    0.39
     '!
    0.38
    ন্তা
    0.37
    oniazid
    0.37
     '*
    0.37
    POSITIVE LOGITS
    ---
    0.44
     입력
    0.43
    ·
    0.41
    ；
    0.41
    ..
    0.40
    ・・・
    0.38
    Ø
    0.38
     ---
    0.37
     üzere
    0.37
     –
    0.37
    Activations Density 0.005%

    No Known Activations