© 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. 139011
    Prev
    Next
    INDEX
    Explanations

    harmful actions

    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
    ാല
    0.46
    aas
    0.41
    ρυ
    0.38
    eating
    0.38
     wrath
    0.38
    λικ
    0.38
    笃
    0.37
    waved
    0.37
    Database
    0.37
     makan
    0.37
    POSITIVE LOGITS
     Beat
    0.50
     учеб
    0.44
    Beat
    0.43
     teach
    0.42
    踢
    0.41
     Unterricht
    0.40
     teacher
    0.40
     professores
    0.39
    教师
    0.38
     สอน
    0.38
    Activations Density 0.001%

    No Known Activations