© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7112
    Prev
    Next
    INDEX
    Explanations

    neurotic self-destructive tendencies

    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_40_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
    ổ
    0.43
     crying
    0.41
    scre
    0.40
     sighed
    0.40
     breath
    0.38
    Panic
    0.38
     screaming
    0.38
     screams
    0.38
    scription
    0.38
     scream
    0.38
    POSITIVE LOGITS
    зова
    0.41
    менту
    0.40
    蝓
    0.39
     guar
    0.39
     Ravens
    0.38
    सीमा
    0.38
     odour
    0.38
    白
    0.38
     Bryan
    0.37
     EditText
    0.37
    Activations Density 0.116%

    No Known Activations