© 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. 165823
    Prev
    Next
    INDEX
    Explanations

    spoiling

    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
    몰
    0.40
    挍
    0.39
     owing
    0.37
     IOC
    0.36
     phyl
    0.35
     preval
    0.34
     Polish
    0.34
    拦
    0.34
     пола
    0.34
     কেন
    0.34
    POSITIVE LOGITS
    conj
    0.37
    ंग्रेस
    0.37
    <unused0>
    0.36
    supports
    0.36
    πους
    0.35
    సింది
    0.35
     parturient
    0.35
    conjug
    0.34
    νες
    0.34
    navigation
    0.34
    Activations Density 0.000%

    No Known Activations