© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82114
    Prev
    Next
    INDEX
    Explanations

    forged / forgive

    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_0_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
     can
    1.68
    ي
    1.61
    يد
    1.59
    ри
    1.57
    ri
    1.55
    aa
    1.51
    ോഷ്യ
    1.30
    j
    1.29
    你
    1.24
    你了
    1.21
    POSITIVE LOGITS
    the
    1.75
    지
    1.37
    ουν
    1.32
     at
    1.29
    ्य
    1.28
    مه
    1.27
    би
    1.23
    ต์
    1.20
    मा
    1.19
    טי
    1.16
    Activations Density 0.001%

    No Known Activations