© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218041
    Prev
    Next
    INDEX
    Explanations

    programming tools

    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_47_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
    ómo
    0.45
    bedo
    0.38
     ühe
    0.38
     audio
    0.37
     ऑडियो
    0.37
     ಈ
    0.36
    இந்
    0.36
     Audio
    0.35
     الاحت
    0.35
     isa
    0.35
    POSITIVE LOGITS
     Sh
    0.43
    ශ
    0.42
    Sh
    0.41
    蛍光
    0.40
    站在
    0.39
     resor
    0.38
    eosin
    0.38
    lander
    0.37
     Ress
    0.37
     standstill
    0.37
    Activations Density 0.000%

    No Known Activations