© 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. 137764
    Prev
    Next
    INDEX
    Explanations

    Education qualifications

    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
     مدت
    0.41
     jah
    0.39
    馊
    0.38
    캥
    0.38
     വലിയ
    0.38
     رحمه
    0.36
    型号
    0.36
     চিং
    0.36
     vrchol
    0.36
     nueve
    0.35
    POSITIVE LOGITS
     شم
    0.45
    夰
    0.39
    ਣ
    0.39
     ற
    0.38
     gathers
    0.38
    picable
    0.37
    pickup
    0.37
    픽
    0.37
     científ
    0.36
    ピック
    0.36
    Activations Density 0.000%

    No Known Activations