© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193150
    Prev
    Next
    INDEX
    Explanations

    habitat, friendship, ongoing actions

    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_4_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
    _
    1.19
    ,
    0.86
    ')
    0.84
    1
    0.81
    &
    0.81
    D
    0.80
    E
    0.79
    ']
    0.78
     is
    0.77
    ılı
    0.77
    POSITIVE LOGITS
    ти
    1.01
    ج
    1.00
    ל
    0.98
    ش
    0.97
    ب
    0.96
    ન
    0.88
    ي
    0.87
    j
    0.86
    ेल
    0.80
    сти
    0.79
    Activations Density 0.000%

    No Known Activations