© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174116
    Prev
    Next
    INDEX
    Explanations

    autofocus, lock on, focal length, face retouch

    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_20_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
     pyrid
    0.45
    翛
    0.43
     medic
    0.43
    ⁴
    0.42
    Previous
    0.42
     музы
    0.41
     Retrie
    0.40
     puriso
    0.39
    蓥
    0.39
    诒
    0.39
    POSITIVE LOGITS
     centerpiece
    0.45
     Cambodian
    0.44
     রাজধানী
    0.44
    adir
    0.43
     резко
    0.43
    camb
    0.43
    ala
    0.43
    and
    0.42
    la
    0.42
     Cambodia
    0.42
    Activations Density 0.000%

    No Known Activations