© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81221
    Prev
    Next
    INDEX
    Explanations

    quirks

    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_0_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
    y
    1.55
    is
    1.51
     avanz
    1.41
    al
    1.37
    n
    1.33
    ار
    1.31
    ก่อน
    1.31
    ช่วง
    1.27
    ী
    1.27
     agua
    1.25
    POSITIVE LOGITS
    />
    1.39
    ية
    1.35
    ast
    1.22
    וד
    1.20
    0
    1.18
    OT
    1.16
     not
    1.13
    ib
    1.13
    ро
    1.12
    ot
    1.11
    Activations Density 0.001%

    No Known Activations