© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65309
    Prev
    Next
    INDEX
    Explanations

    youth sports

    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_46_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
     braking
    0.41
     gall
    0.38
     disgust
    0.38
    验收
    0.36
     noise
    0.36
     Herod
    0.36
     retort
    0.35
    回
    0.35
    成熟
    0.35
     discontent
    0.35
    POSITIVE LOGITS
     scoreboard
    0.43
     bowl
    0.40
    province
    0.40
     Lesson
    0.39
     попробовать
    0.39
     RUN
    0.39
     Sr
    0.39
     मनोवैज्ञानिक
    0.39
    bowl
    0.39
     இறைவன்
    0.38
    Activations Density 0.000%

    No Known Activations