© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168056
    Prev
    Next
    INDEX
    Explanations

    solving equations with x

    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_34_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
     magic
    0.41
    берриз
    0.37
     才
    0.37
     डॉट
    0.36
     perverse
    0.36
     బీ
    0.36
     prefix
    0.36
     زیادی
    0.35
     魔
    0.34
     exuberant
    0.34
    POSITIVE LOGITS
     rapporto
    0.52
    奭
    0.44
     ensayos
    0.41
    شاركة
    0.40
    gestaltung
    0.39
    жерела
    0.39
    ゎ
    0.39
     rapporti
    0.38
     هون
    0.38
    醮
    0.38
    Activations Density 0.002%

    No Known Activations