© 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. 170413
    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
     —
    0.58
     —,
    0.49
     --
    0.48
    —
    0.40
     ---
    0.39
     —¿
    0.37
     "--
    0.37
     Although
    0.37
     {,
    0.37
     "/",
    0.35
    POSITIVE LOGITS
     имају
    0.39
    ították
    0.35
    Можно
    0.35
     having
    0.34
    noxious
    0.34
    having
    0.33
    дження
    0.33
     বাঙালির
    0.33
    following
    0.33
    thresh
    0.33
    Activations Density 0.000%

    No Known Activations