© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212448
    Prev
    Next
    INDEX
    Explanations

    vene a

    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_5_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
     It
    1.75
     You
    1.25
     This
    1.20
     on
    1.19
    It
    1.18
     c
    1.17
     The
    1.16
     These
    1.16
     What
    1.15
     echter
    1.15
    POSITIVE LOGITS
    ق
    1.70
    ب
    1.66
    드
    1.58
    ك
    1.51
    ول
    1.45
    ش
    1.36
    ה
    1.35
    인
    1.32
    트
    1.31
    지
    1.28
    Activations Density 0.000%

    No Known Activations