© 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. 252381
    Prev
    Next
    INDEX
    Explanations

    spe

    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
    plural
    0.44
     plural
    0.41
     탄
    0.40
    탄
    0.39
    琿
    0.37
    reeting
    0.37
    катери
    0.37
    焱
    0.36
    ݢ
    0.36
     Boc
    0.35
    POSITIVE LOGITS
     spe
    3.33
     Spe
    2.69
    Spe
    2.64
    spe
    2.63
     спе
    2.16
     SPE
    2.02
    SPE
    1.80
     bel
    1.74
     Spears
    1.45
     Spear
    1.44
    Activations Density 0.004%

    No Known Activations