© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59239
    Prev
    Next
    INDEX
    Explanations

    float64 or 64-bit data types

    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_2_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
    のは
    1.28
     for
    1.26
    การ
    1.25
     The
    1.11
    기
    1.11
     one
    1.09
    ک
    1.08
     THE
    1.07
     gaya
    1.05
    ש
    1.02
    POSITIVE LOGITS
    től
    1.27
    tól
    1.24
    s
    1.19
    ة
    1.15
    tte
    1.12
    kter
    1.10
    ва
    1.09
    tar
    1.08
    ról
    1.06
    tor
    1.03
    Activations Density 0.016%

    No Known Activations