© 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. 160937
    Prev
    Next
    INDEX
    Explanations

    cave entrances, paintings, systems, walls, depth, diving, man

    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
    マ
    1.23
    ه
    1.23
    مت
    1.20
    アシ
    1.20
    エ
    1.16
    子ども
    1.14
    ご飯
    1.12
     selezione
    1.09
    اً
    1.09
     parete
    1.09
    POSITIVE LOGITS
    -
    1.20
    ة
    0.99
    is
    0.96
    y
    0.92
    ing
    0.92
     I
    0.91
     quell
    0.89
     és
    0.89
    u
    0.88
    ist
    0.87
    Activations Density 0.002%

    No Known Activations