© 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. 253172
    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
     manic
    0.36
     compagnia
    0.36
     dele
    0.36
    --
    0.35
    diendo
    0.35
    леко
    0.34
     momencie
    0.34
    -"
    0.33
     haunting
    0.33
    "
    0.33
    POSITIVE LOGITS
     /
    0.87
     /$
    0.61
     //
    0.57
     /,
    0.57
     ／
    0.55
     /.
    0.52
     /(
    0.51
    :/
    0.50
     $/
    0.49
     /\
    0.49
    Activations Density 0.011%

    No Known Activations