© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24899
    Prev
    Next
    INDEX
    Explanations

    V-shaped, notch, tail, grip, class

    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_10_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
    ’
    0.23
     planned
    0.20
    ћ
    0.18
    0.18
     hacking
    0.18
    Maps
    0.18
    甚
    0.17
     حالا
    0.17
    此事
    0.17
    hern
    0.17
    POSITIVE LOGITS
    то
    0.27
    ра
    0.27
    ל
    0.26
    ad
    0.24
    াল
    0.24
    ת
    0.23
     Selección
    0.23
     cittadini
    0.23
    та
    0.22
     Entrenamiento
    0.22
    Activations Density 0.005%

    No Known Activations