© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206849
    Prev
    Next
    INDEX
    Explanations

    sounds good

    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_20_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
     Galactic
    0.27
     lá
    0.25
     Rad
    0.25
     legjob
    0.23
    覷
    0.23
     drastic
    0.23
    നട
    0.23
    Boltzmann
    0.22
     Metadata
    0.22
    ல
    0.22
    POSITIVE LOGITS
     counterfe
    0.27
     ሽፋን
    0.27
    ypass
    0.27
     государственных
    0.26
    াইন
    0.26
     جميع
    0.25
    etva
    0.25
    ivi
    0.24
     перейти
    0.24
     وات
    0.24
    Activations Density 0.002%

    No Known Activations