© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1456
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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_39_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
     Hamid
    0.46
     Nasir
    0.38
     motiva
    0.38
    omitem
    0.38
    hamed
    0.37
     Samir
    0.37
    唥
    0.37
     tunt
    0.37
     Political
    0.36
    ("^
    0.36
    POSITIVE LOGITS
    zas
    0.36
    infos
    0.35
    info
    0.34
    event
    0.32
    VERSE
    0.31
    Morning
    0.31
    вах
    0.30
    call
    0.30
    late
    0.30
     event
    0.30
    Activations Density 0.018%

    No Known Activations