© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53454
    Prev
    Next
    INDEX
    Explanations

    reporting verb followed by speaker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
    katana
    0.40
    装
    0.38
     WOW
    0.38
     wow
    0.37
     ध्व
    0.37
     असंख्य
    0.37
    ledning
    0.36
    make
    0.36
    tts
    0.36
    winds
    0.36
    POSITIVE LOGITS
     indicó
    0.44
     قالت
    0.43
    ("../
    0.41
     afirmó
    0.40
    ,’’
    0.40
     olmadığını
    0.39
     ".",
    0.39
     উপজেলার
    0.38
     says
    0.38
    ,"
    0.38
    Activations Density 0.000%

    No Known Activations