© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68818
    Prev
    Next
    INDEX
    Explanations

    Mongolia

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    الد
    0.41
    <0x93>
    0.41
     ד
    0.40
     taş
    0.40
     دين
    0.40
    ਦ
    0.39
    
    0.39
     simpl
    0.39
    ד
    0.39
     सिंप
    0.39
    POSITIVE LOGITS
     Hul
    0.43
    يته
    0.39
    वात
    0.38
    mangle
    0.38
     proliferate
    0.38
    াইতে
    0.37
    ItemGroup
    0.37
    हुल
    0.37
     Aiken
    0.37
    ঘরে
    0.37
    Activations Density 0.000%

    No Known Activations