© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50679
    Prev
    Next
    INDEX
    Explanations

    amounts and durations

    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_31_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
    ută
    0.40
    ويب
    0.38
     चिंता
    0.37
    лід
    0.36
     серд
    0.35
    pmod
    0.35
    ($_
    0.34
    लि
    0.34
     resonance
    0.34
    irting
    0.34
    POSITIVE LOGITS
     erfahren
    0.38
     forces
    0.38
     apiClient
    0.36
    maxY
    0.36
    ляция
    0.36
    dummies
    0.35
     Innovation
    0.35
     شوی
    0.35
    垫
    0.34
    권을
    0.34
    Activations Density 0.009%

    No Known Activations