© 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. 253262
    Prev
    Next
    INDEX
    Explanations

    come arrive

    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
     direct
    0.45
    —
    0.44
    direct
    0.42
     yard
    0.39
     लहान
    0.39
     Direct
    0.39
    Direct
    0.39
    --(
    0.39
     വ്യത്യ
    0.38
     Yard
    0.37
    POSITIVE LOGITS
     close
    0.42
     Sm
    0.40
     quickly
    0.39
     Fe
    0.39
    🍩
    0.37
    close
    0.37
     Cig
    0.36
     نه
    0.36
    Fe
    0.35
     speedily
    0.35
    Activations Density 0.000%

    No Known Activations