© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66678
    Prev
    Next
    INDEX
    Explanations

    specific entities

    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_51_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
     آمده
    0.44
     আহমেদ
    0.41
    竺
    0.40
     দেবতার
    0.39
    डेन
    0.39
    হন
    0.39
     phố
    0.38
     احمد
    0.38
    toa
    0.38
     സഹ
    0.38
    POSITIVE LOGITS
    Encryption
    0.42
    瓦
    0.40
    witch
    0.39
     dia
    0.38
    qst
    0.37
    Eid
    0.37
    JSON
    0.36
     Bat
    0.36
    Warner
    0.36
    jpe
    0.36
    Activations Density 0.005%

    No Known Activations