© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206039
    Prev
    Next
    INDEX
    Explanations

    up

    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
    看出
    0.40
    jah
    0.39
    imized
    0.39
    曉
    0.38
     IMPLIED
    0.36
     GOOD
    0.35
    ИА
    0.35
    ogeneities
    0.34
    的思想
    0.34
     zeigen
    0.34
    POSITIVE LOGITS
     ire
    0.45
     sam
    0.40
     sams
    0.40
     date
    0.39
     Padukone
    0.38
    따
    0.38
     Brahm
    0.37
     CNRS
    0.37
     Ire
    0.37
     idam
    0.37
    Activations Density 0.000%

    No Known Activations