© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63919
    Prev
    Next
    INDEX
    Explanations

    surfing and water sports

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     P
    0.41
     யூ
    0.40
     nailed
    0.40
    Fut
    0.39
    <0x89>
    0.39
     Mast
    0.39
     melts
    0.39
     případ
    0.39
    स्ताव
    0.38
    county
    0.38
    POSITIVE LOGITS
     "-----
    0.41
     GPI
    0.40
    gsm
    0.40
     सिक्स
    0.39
     GSM
    0.38
    ECH
    0.37
     தொழில்
    0.36
     IVA
    0.36
    PopupMenu
    0.35
    ເລ
    0.35
    Activations Density 0.010%

    No Known Activations