© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15021
    Prev
    Next
    INDEX
    Explanations

    shotguns or projectiles

    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_15_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
    Terminology
    0.48
    UN
    0.46
     iniciativas
    0.46
    Rio
    0.45
    Dm
    0.45
     estamp
    0.45
    RNB
    0.45
    </b>
    0.44
     أج
    0.44
    म्भ
    0.44
    POSITIVE LOGITS
    ꒪
    0.55
    \">
    0.54
     blackberry
    0.54
     least
    0.52
     huyện
    0.52
    एसआय
    0.51
     $^{\
    0.51
     powiat
    0.51
    鄢
    0.50
     पुढील
    0.50
    Activations Density 0.001%

    No Known Activations