© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205237
    Prev
    Next
    INDEX
    Explanations

    half devil

    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_46_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
     конститу
    0.42
     அரசிய
    0.39
    ంబేద్
    0.39
    ത്തിനു
    0.38
    Displayed
    0.37
     Конститу
    0.36
     퇴
    0.36
     मालिनी
    0.36
     Tully
    0.35
    頩
    0.35
    POSITIVE LOGITS
     devil
    0.44
    Ру
    0.41
     devils
    0.41
    half
    0.40
    Half
    0.39
     demons
    0.38
     Half
    0.38
    Fro
    0.38
     دشمن
    0.37
     לכ
    0.37
    Activations Density 0.000%

    No Known Activations