© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36170
    Prev
    Next
    INDEX
    Explanations

    trip plans

    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_11_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
    ಿಯು
    0.59
    ⵥ
    0.56
    family
    0.52
     സന്ത
    0.52
    enov
    0.52
    mediaDevices
    0.52
    et
    0.51
    ಾವ್
    0.51
     descendants
    0.50
    akoti
    0.50
    POSITIVE LOGITS
    \
    0.71
    :
    0.70
    те
    0.60
    ties
    0.59
    ته
    0.59
    ड़ी
    0.57
    sofar
    0.57
    Prefs
    0.57
    Timer
    0.55
     والخ
    0.55
    Activations Density 0.001%

    No Known Activations