© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196615
    Prev
    Next
    INDEX
    Explanations

    football players

    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_46_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
    蕉
    0.44
    Worlds
    0.43
    リート
    0.41
    World
    0.39
    Barb
    0.39
    ্ল্ড
    0.39
     World
    0.38
    }^{(
    0.37
     Barb
    0.37
    擎
    0.36
    POSITIVE LOGITS
    사진
    0.40
     triển
    0.39
    غت
    0.38
     ঈদ
    0.38
    잍
    0.38
    photography
    0.37
     photographic
    0.37
     lég
    0.36
    sear
    0.36
    future
    0.36
    Activations Density 0.000%

    No Known Activations