© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123113
    Prev
    Next
    INDEX
    Explanations

    aldehyde, sheath, ite

    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_3_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
     \
    0.70
    ר
    0.67
    ྞ
    0.63
    दर्शिता
    0.62
    ϓ
    0.58
     bakery
    0.56
    虻
    0.56
     auditorium
    0.55
    ීය
    0.55
     not
    0.55
    POSITIVE LOGITS
    та
    0.96
    that
    0.88
    as
    0.86
    ا
    0.84
    on
    0.76
    ter
    0.74
    ו
    0.74
    :
    0.73
    ти
    0.72
    in
    0.71
    Activations Density 0.000%

    No Known Activations