© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80448
    Prev
    Next
    INDEX
    Explanations

    answer followed by specific choices

    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_31_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
    ጒ
    0.41
     strokes
    0.38
     ဂ
    0.38
     waterfalls
    0.36
     differentials
    0.36
     spur
    0.34
     zmi
    0.34
     intents
    0.34
    व्यू
    0.34
     purposely
    0.34
    POSITIVE LOGITS
    ický
    0.36
    നും
    0.36
    ::*;
    0.34
    oticons
    0.34
    čil
    0.34
    äure
    0.33
     aide
    0.33
    htein
    0.33
    τικές
    0.32
     أخ
    0.32
    Activations Density 0.011%

    No Known Activations