© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48958
    Prev
    Next
    INDEX
    Explanations

    places and amenities

    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_31_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
     francia
    0.29
    categorias
    0.27
    航
    0.26
     asterisk
    0.26
    french
    0.26
     Donner
    0.26
    グ
    0.26
     februar
    0.25
     França
    0.25
     French
    0.25
    POSITIVE LOGITS
    îte
    0.33
    ٓ
    0.32
     cuyos
    0.30
    ThemeOverlay
    0.29
    乡
    0.28
     तालुका
    0.27
    pImage
    0.27
     zásobníku
    0.27
     cuyas
    0.27
    msubsup
    0.27
    Activations Density 0.005%

    No Known Activations