© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235220
    Prev
    Next
    INDEX
    Explanations

    gigabytes

    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
     JV
    0.42
    getPort
    0.40
    肅
    0.38
    Semitism
    0.38
     España
    0.38
     Ports
    0.38
    andung
    0.38
     Concepts
    0.37
     deres
    0.37
    ΑΣ
    0.37
    POSITIVE LOGITS
    anday
    0.38
    ukary
    0.37
    ירים
    0.36
    孺
    0.36
     உய
    0.35
    情報
    0.35
    的具体
    0.35
    情报
    0.34
     daylight
    0.34
     adversaries
    0.33
    Activations Density 0.001%

    No Known Activations