© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33447
    Prev
    Next
    INDEX
    Explanations

    gynecologist, orthodontist

    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_7_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
    ă
    0.18
     respirator
    0.18
     was
    0.17
    า
    0.17
     a
    0.16
    ৫
    0.16
    on
    0.16
    LER
    0.15
    ER
    0.15
    ")
    0.15
    POSITIVE LOGITS
    v
    0.18
    h
    0.17
    ры
    0.15
    ми
    0.14
     leftmost
    0.14
     дороже
    0.14
    ки
    0.14
    ил
    0.14
    nd
    0.14
    ро
    0.13
    Activations Density 0.001%

    No Known Activations