© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214437
    Prev
    Next
    INDEX
    Explanations

    mentally unstable

    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_5_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
    plikasi
    1.06
    ق
    1.05
    ка
    1.03
    can
    0.89
    ف
    0.86
    بینی
    0.86
    RelativeLayout
    0.85
    ya
    0.84
     argumentative
    0.84
    c
    0.83
    POSITIVE LOGITS
    s
    1.89
    ्स
    1.42
    ओं
    1.41
    ের
    1.38
    ς
    1.37
    es
    1.35
    ন
    1.32
    ة
    1.30
    स
    1.28
    ों
    1.25
    Activations Density 0.000%

    No Known Activations