© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31097
    Prev
    Next
    INDEX
    Explanations

    speed measurements (km/h or mph)

    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_31_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
     strengths
    0.35
     improv
    0.34
     cloud
    0.30
     Impro
    0.30
     incertid
    0.30
     expertos
    0.29
     %)
    0.29
    尺度
    0.29
     ilma
    0.29
     vides
    0.29
    POSITIVE LOGITS
    Lantern
    0.31
     ሁሉ
    0.30
    SpawnEntry
    0.29
    orderEntry
    0.29
     Hàm
    0.29
    }}:=\
    0.29
    起来
    0.28
    Origin
    0.28
    îte
    0.28
    ayv
    0.28
    Activations Density 0.002%

    No Known Activations