© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43582
    Prev
    Next
    INDEX
    Explanations

    GUI label declarations

    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_22_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
     asociados
    0.39
     lediglich
    0.39
    τ
    0.38
     Million
    0.38
    pom
    0.38
     vaid
    0.38
    ന്വേഷ
    0.38
    ok
    0.37
    IDAD
    0.37
     unabhäng
    0.37
    POSITIVE LOGITS
     外
    0.43
     gram
    0.43
     scor
    0.41
     иностран
    0.41
     мето
    0.40
     முறை
    0.37
    簟
    0.37
    Be
    0.37
     быть
    0.37
    нера
    0.37
    Activations Density 0.001%

    No Known Activations