© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108323
    Prev
    Next
    INDEX
    Explanations

    phishing, phrasal, phobos, phasmophobia

    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_2_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
    '
    1.85
    ו
    1.66
    ’
    1.62
    و
    1.58
    ุ
    1.52
    ো
    1.39
    ب
    1.27
    ુ
    1.23
    ির
    1.21
    >
    1.16
    POSITIVE LOGITS
    t
    1.67
     I
    1.37
    ng
    1.35
    k
    1.33
    c
    1.27
    ll
    1.23
    nt
    1.20
     ۸
    1.17
    v
    1.17
    dengan
    1.16
    Activations Density 0.001%

    No Known Activations