© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50160
    Prev
    Next
    INDEX
    Explanations

    comes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     partiellement
    0.43
     tightly
    0.42
    鱉
    0.41
     strictly
    0.41
     Partially
    0.41
     strictement
    0.39
     partially
    0.38
    𝚎
    0.38
     partly
    0.37
     Partly
    0.37
    POSITIVE LOGITS
     accolades
    0.48
     laude
    0.45
     forState
    0.44
    目的地
    0.43
     andare
    0.43
     though
    0.40
     syllables
    0.39
     attempts
    0.38
     déplacer
    0.38
     stares
    0.37
    Activations Density 0.004%

    No Known Activations