© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137247
    Prev
    Next
    INDEX
    Explanations

    visual event system

    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_37_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
    ନ୍
    0.45
     plufieurs
    0.40
    يفي
    0.39
     sceGu
    0.39
     होस्ट
    0.37
    กฎ
    0.36
    直し
    0.36
    酲
    0.36
    িষ্ট
    0.36
     социальной
    0.36
    POSITIVE LOGITS
     clips
    0.44
     reminiscent
    0.43
     cross
    0.41
     CLIP
    0.40
     Clip
    0.39
     did
    0.39
     Clips
    0.39
     fair
    0.38
    clips
    0.38
     rec
    0.37
    Activations Density 0.001%

    No Known Activations