© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9954
    Prev
    Next
    INDEX
    Explanations

    Food/Drink

    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_13_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
    Generate
    0.29
    Won
    0.29
     formant
    0.28
    Creates
    0.28
    威
    0.28
     सतह
    0.27
     생성
    0.26
    뢰
    0.26
    に関する
    0.26
    гат
    0.26
    POSITIVE LOGITS
    önen
    0.30
     pastries
    0.29
    ool
    0.28
    olid
    0.28
     Coffee
    0.28
    izadas
    0.28
    ütte
    0.28
     Kaffee
    0.28
     vyber
    0.28
    opa
    0.27
    Activations Density 0.001%

    No Known Activations