© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44298
    Prev
    Next
    INDEX
    Explanations

    end of a phrase or sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     आश्रम
    0.67
     Einrichtungen
    0.55
     sabbam
    0.54
     आलिया
    0.54
     monasteries
    0.53
    㢦
    0.52
    CNR
    0.51
     hypothalam
    0.51
    Բ
    0.50
     baseX
    0.50
    POSITIVE LOGITS
     flavor
    0.54
    ion
    0.50
     rabbit
    0.50
    intention
    0.50
    ival
    0.48
    in
    0.47
    is
    0.46
     created
    0.46
    full
    0.46
    連續
    0.46
    Activations Density 0.014%

    No Known Activations