© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133982
    Prev
    Next
    INDEX
    Explanations

    conversational turns

    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_50_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
     mule
    0.41
     mercenaries
    0.40
    idE
    0.39
     mules
    0.38
     Mint
    0.38
     ስ
    0.38
     ling
    0.37
    霎
    0.37
     mint
    0.37
     Rashid
    0.37
    POSITIVE LOGITS
    谙
    0.43
     அறி
    0.43
     pover
    0.39
    regate
    0.38
     рекоменду
    0.37
     Franco
    0.37
     Tommy
    0.37
    azgo
    0.37
     кот
    0.36
     करणारे
    0.36
    Activations Density 0.007%

    No Known Activations