© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31116
    Prev
    Next
    INDEX
    Explanations

    say minutes

    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_50_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
     دس
    0.41
    bookmarks
    0.39
    Dol
    0.38
    –
    0.38
     oon
    0.37
     chacune
    0.37
    stuffs
    0.36
     secretions
    0.36
     ful
    0.35
    novu
    0.35
    POSITIVE LOGITS
    ᴦ
    0.37
    𝘃
    0.35
    >');
    0.31
    𝗮
    0.31
    호를
    0.31
    acking
    0.31
    avons
    0.31
    orting
    0.30
    ടുന്ന
    0.30
    ത്തുന്ന
    0.30
    Activations Density 0.012%

    No Known Activations