© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51930
    Prev
    Next
    INDEX
    Explanations

    executed signatures

    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_31_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
     sacram
    0.41
     Lazar
    0.37
     marcher
    0.37
    로우
    0.36
    恭
    0.36
     уста
    0.35
    igata
    0.35
    cest
    0.35
     sacrament
    0.35
    localtime
    0.35
    POSITIVE LOGITS
    ັ
    0.37
    完璧
    0.34
    ข้าง
    0.33
     alvo
    0.32
    ξι
    0.32
    zeń
    0.31
     এইরূপে
    0.30
     связи
    0.30
    励
    0.30
     apoio
    0.30
    Activations Density 0.000%

    No Known Activations