© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141834
    Prev
    Next
    INDEX
    Explanations

    daring expeditions, adventures, designs

    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_12_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
     Aspects
    0.61
    frastructure
    0.58
    ı
    0.55
     Баскетбол
    0.55
    cı
    0.54
    جراء
    0.53
    asov
    0.52
    裟
    0.52
     رجسٹ
    0.52
     খবর
    0.51
    POSITIVE LOGITS
     brave
    0.63
     fé
    0.61
     farmhouse
    0.59
     pliable
    0.59
     MU
    0.58
     bold
    0.58
     daring
    0.58
    >
    0.57
     flight
    0.57
     unwilling
    0.57
    Activations Density 0.000%

    No Known Activations