© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107771
    Prev
    Next
    INDEX
    Explanations

    Amara or Ira followed by specific words

    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_1_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
    да
    1.45
     in
    1.21
    arı
    1.21
    EL
    1.14
    AR
    1.13
    та
    1.09
    erci
    1.06
    >
    1.04
    िड
    1.03
    ５
    1.02
    POSITIVE LOGITS
     to
    1.34
    v
    1.20
    re
    1.17
    p
    1.16
    ص
    1.13
     I
    1.12
    b
    1.11
    h
    1.07
    เป็น
    1.06
    对
    1.02
    Activations Density 0.000%

    No Known Activations