© 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. 205645
    Prev
    Next
    INDEX
    Explanations

    recite

    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
    Sco
    0.46
     Scoop
    0.42
     Sco
    0.41
     透明
    0.40
    &
    0.39
     AFP
    0.38
    轱
    0.38
    RIX
    0.37
     cob
    0.37
     Cob
    0.37
    POSITIVE LOGITS
     recite
    1.35
     recital
    1.33
     recited
    1.22
     recitation
    1.22
     reciting
    1.19
    念
    1.13
     Rec
    0.99
     rec
    0.96
    rec
    0.96
    Rec
    0.91
    Activations Density 0.000%

    No Known Activations