© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202787
    Prev
    Next
    INDEX
    Explanations

    hard painful

    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
    ৈত
    0.44
    PlatformVersion
    0.40
    LIMIT
    0.39
     dian
    0.39
    antibody
    0.39
    pictures
    0.38
    éviter
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.37
    river
    0.37
    volume
    0.36
    POSITIVE LOGITS
     hard
    0.60
     Hard
    0.49
     HARD
    0.46
     painful
    0.43
    硬
    0.42
     duro
    0.41
     कठिन
    0.40
     Blak
    0.40
     tough
    0.40
     hardest
    0.40
    Activations Density 0.004%

    No Known Activations