© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192880
    Prev
    Next
    INDEX
    Explanations

    "een" followed by months or syllables

    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_4_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
    い
    0.36
    <0x80>
    0.31
    ult
    0.31
    ि
    0.30
    ia
    0.29
    that
    0.29
    ियों
    0.29
    ва
    0.28
    한
    0.28
    ü
    0.28
    POSITIVE LOGITS
     accumulates
    0.36
     sureties
    0.35
     accuses
    0.35
     президен
    0.35
    ang
    0.35
     chimiques
    0.34
     underlies
    0.34
    おすすめ
    0.34
    ಾ
    0.34
     exemplifies
    0.34
    Activations Density 0.001%

    No Known Activations