© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107005
    Prev
    Next
    INDEX
    Explanations

    usually followed by a verb

    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     виды
    1.20
     вигляді
    1.15
     годы
    1.14
     ל
    1.06
     propias
    1.05
     правило
    1.05
     been
    1.04
     родители
    1.02
     παιδιά
    1.02
     hardships
    1.00
    POSITIVE LOGITS
    on
    1.35
    N
    1.34
    y
    1.30
    c
    1.20
    K
    1.20
    V
    1.17
    am
    1.09
    žas
    1.05
    ية
    1.05
    ник
    1.04
    Activations Density 0.000%

    No Known Activations