© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259750
    Prev
    Next
    INDEX
    Explanations

    defend against, defending a person/group

    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_22_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
     мая
    0.47
    Geocoder
    0.45
     idxf
    0.45
     elastomer
    0.43
     purus
    0.43
     anisotropic
    0.42
     Ф
    0.41
     中古
    0.41
     KBS
    0.41
     পর্যাপ্ত
    0.41
    POSITIVE LOGITS
    lek
    0.49
    ätt
    0.42
    settings
    0.39
    Preference
    0.39
    Served
    0.38
    ربع
    0.38
     tartoz
    0.37
     ಸೇವ
    0.37
    Consumed
    0.36
     graduated
    0.36
    Activations Density 0.000%

    No Known Activations