© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200326
    Prev
    Next
    INDEX
    Explanations

    reference

    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
     hastalık
    0.45
    IDTH
    0.42
    CAF
    0.41
     mån
    0.40
    APH
    0.38
    ṅ
    0.38
     AFD
    0.37
    Mf
    0.37
    ₅
    0.37
     artikkel
    0.37
    POSITIVE LOGITS
    ring
    0.39
     relate
    0.37
    링
    0.37
    ringing
    0.36
    τία
    0.36
     ringing
    0.34
     سلام
    0.34
    esser
    0.34
    ral
    0.33
    elli
    0.33
    Activations Density 0.000%

    No Known Activations