© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15476
    Prev
    Next
    INDEX
    Explanations

    beá, sin, without

    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_40_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
     decorated
    0.43
     Christen
    0.40
     JSP
    0.40
     Colin
    0.39
     skinned
    0.38
     veamos
    0.38
    桢
    0.38
    onOptions
    0.38
     Connecting
    0.37
     Bex
    0.37
    POSITIVE LOGITS
    argo
    0.39
    auge
    0.37
    ARG
    0.35
    λή
    0.34
     aufgel
    0.34
     Bedürfnisse
    0.33
    }^{+
    0.33
     গেল
    0.33
    原來
    0.32
    ഭ്യാ
    0.32
    Activations Density 0.026%

    No Known Activations