© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139275
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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_46_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
    Suggest
    0.39
    なわち
    0.38
    粗
    0.38
     retrieved
    0.37
    Retrie
    0.37
    教
    0.36
    嗜
    0.36
    找到
    0.35
    indazol
    0.35
    Retrieve
    0.35
    POSITIVE LOGITS
    cers
    0.44
     PACK
    0.41
     commissions
    0.39
     adam
    0.39
     apprentices
    0.38
     railways
    0.38
     mel
    0.38
    mel
    0.37
     outings
    0.37
     railroads
    0.37
    Activations Density 0.001%

    No Known Activations