© 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. 137500
    Prev
    Next
    INDEX
    Explanations

    Yeats poems

    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
    Bang
    0.41
    DTD
    0.40
    emph
    0.39
    bigsqcup
    0.38
    Disable
    0.37
    bam
    0.36
    ,&
    0.35
     KIM
    0.35
     Oph
    0.35
     Emirates
    0.34
    POSITIVE LOGITS
     $:=$
    0.46
     rising
    0.44
     Pala
    0.43
    座椅
    0.42
     Drei
    0.41
     Rising
    0.41
     Stretching
    0.40
    делать
    0.40
    イール
    0.40
     terra
    0.39
    Activations Density 0.000%

    No Known Activations