© 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. 11515
    Prev
    Next
    INDEX
    Explanations

    to * applying

    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
     après
    0.27
    éu
    0.25
    économ
    0.24
    I
    0.24
    ặt
    0.23
    ți
    0.23
    après
    0.23
    rxjs
    0.22
     după
    0.22
    </sup>
    0.22
    POSITIVE LOGITS
    Ნ
    0.26
     এটাও
    0.22
    负
    0.22
    ಂಭ
    0.22
    Დ
    0.22
     কাজেই
    0.21
    讽
    0.21
     bookings
    0.20
     realizations
    0.20
    也就
    0.20
    Activations Density 0.023%

    No Known Activations