© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1539
    Prev
    Next
    INDEX
    Explanations

    hidden or inaccessible concepts

    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_39_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
    clusion
    0.45
     dop
    0.40
    ोड
    0.37
     jako
    0.37
     끌
    0.36
    unicate
    0.36
    Were
    0.35
     ιδ
    0.35
     rê
    0.34
     po
    0.34
    POSITIVE LOGITS
     embedded
    0.45
    管理者
    0.43
    委員會
    0.39
     Waiting
    0.37
     DIY
    0.37
    成本
    0.37
    处理器
    0.37
    Embedded
    0.36
    embedded
    0.36
    ༞
    0.36
    Activations Density 0.045%

    No Known Activations