© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44238
    Prev
    Next
    INDEX
    Explanations

    explaining not logical

    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_13_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
     Dunham
    0.58
    ppard
    0.56
    ży
    0.55
    zien
    0.54
    rootDir
    0.54
    ỹ
    0.53
    hoe
    0.53
    ena
    0.52
    iden
    0.52
    führ
    0.52
    POSITIVE LOGITS
    アル
    0.60
    이
    0.59
     condolences
    0.56
    áticas
    0.55
    탄
    0.55
    alleg
    0.53
    人で
    0.53
     missiles
    0.53
    לי
    0.52
    谷
    0.52
    Activations Density 0.010%

    No Known Activations