© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156855
    Prev
    Next
    INDEX
    Explanations

    books

    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_50_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
    lab
    0.44
     LAB
    0.37
    ickness
    0.37
     profitably
    0.37
    nel
    0.36
    }^{*}=\
    0.36
    野
    0.36
    unun
    0.36
    NO
    0.36
     lab
    0.35
    POSITIVE LOGITS
     سبيل
    0.38
     VIH
    0.37
     vesicle
    0.37
     steric
    0.37
    灬
    0.37
     três
    0.37
    modation
    0.37
    ेशन
    0.36
    బ్యా
    0.36
     Rae
    0.36
    Activations Density 0.004%

    No Known Activations