© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129456
    Prev
    Next
    INDEX
    Explanations

    school principal

    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_1_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
    of
    1.34
    aste
    0.90
    ý
    0.89
    ibilities
    0.88
    man
    0.86
    oming
    0.86
    osi
    0.85
    在
    0.85
    AR
    0.84
    ading
    0.84
    POSITIVE LOGITS
    ه
    1.50
    ת
    1.30
    ت
    1.30
    на
    1.26
    ل
    1.24
    т
    1.23
    м
    1.12
    هما
    1.11
    ﺕ
    1.11
    त
    1.10
    Activations Density 0.001%

    No Known Activations