© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87564
    Prev
    Next
    INDEX
    Explanations

    disregards safety, protocol, guidelines

    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_3_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
    kotlin
    0.73
    ка
    0.71
    か
    0.66
    ɖ
    0.64
     doesn
    0.63
    ཆ
    0.62
    ipv
    0.60
    дку
    0.59
    ༤
    0.59
    Servlet
    0.58
    POSITIVE LOGITS
    \},
    0.66
    و
    0.64
     linie
    0.60
    ,
    0.60
    হ
    0.60
    TO
    0.58
     Ih
    0.58
    organisms
    0.57
    ক
    0.57
     Auger
    0.55
    Activations Density 0.000%

    No Known Activations