© 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. 259259
    Prev
    Next
    INDEX
    Explanations

    designed with X in mind

    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
     organized
    0.44
     sequenced
    0.43
    ////////////////
    0.42
     educational
    0.42
     özel
    0.41
     organizing
    0.41
    گم
    0.41
    并
    0.41
     moderated
    0.40
    通用
    0.40
    POSITIVE LOGITS
     Sebagai
    0.46
    Sebagai
    0.43
     Aron
    0.43
    artner
    0.42
     apartness
    0.42
     Søren
    0.41
     Lyapunov
    0.40
     као
    0.40
     sebagai
    0.39
     SDG
    0.39
    Activations Density 0.014%

    No Known Activations