© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148869
    Prev
    Next
    INDEX
    Explanations

    word endings

    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_59_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
     acest
    0.52
     Acest
    0.43
    h
    0.40
    hui
    0.35
    ្ស
    0.35
    وما
    0.35
    hal
    0.33
    o
    0.33
    ޓ
    0.33
    on
    0.33
    POSITIVE LOGITS
    eless
    0.55
    encio
    0.49
    ing
    0.44
    ención
    0.42
    enz
    0.41
    encja
    0.41
    ánico
    0.40
     Congrès
    0.39
    риф
    0.39
     enig
    0.39
    Activations Density 0.000%

    No Known Activations