© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160274
    Prev
    Next
    INDEX
    Explanations

    discontinuation or redistribution

    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_2_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
    י
    1.58
    ა
    1.41
    ir
    1.40
    in
    1.36
    the
    1.34
    ת
    1.25
    ু
    1.19
    ר
    1.18
    il
    1.16
    יות
    1.14
    POSITIVE LOGITS
    습니다
    1.96
    ется
    1.80
     to
    1.70
    我
    1.45
    कर
    1.42
    いて
    1.41
    ння
    1.40
    acji
    1.38
    льные
    1.37
    ρα
    1.36
    Activations Density 0.001%

    No Known Activations