© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208133
    Prev
    Next
    INDEX
    Explanations

    document content

    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_56_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
     Griff
    0.44
    TEE
    0.40
    Returns
    0.39
    nickname
    0.38
    鹜
    0.38
    ;&#
    0.37
     THOR
    0.36
    PASSWORD
    0.36
     Zeits
    0.36
    চ্চার
    0.36
    POSITIVE LOGITS
     macros
    0.48
     macro
    0.44
     Paper
    0.42
    宏
    0.42
     papers
    0.41
     paper
    0.40
     macroeconomic
    0.40
     sheets
    0.40
    Macros
    0.40
    ற்றி
    0.39
    Activations Density 0.001%

    No Known Activations