© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44610
    Prev
    Next
    INDEX
    Explanations

    long-tailed animals/boats

    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_13_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
    čku
    0.50
     сфере
    0.48
     ঈশ্বর
    0.47
    有無
    0.46
    煕
    0.46
     इट
    0.46
     ఉన్నారు
    0.46
     כמו
    0.45
    hemia
    0.45
    犹如
    0.45
    POSITIVE LOGITS
     granit
    0.57
     cp
    0.52
     kayaks
    0.49
     yacht
    0.49
     föret
    0.47
    .$\
    0.47
     Yachts
    0.47
    roleum
    0.46
     (\
    0.46
    produced
    0.46
    Activations Density 0.000%

    No Known Activations