© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174776
    Prev
    Next
    INDEX
    Explanations

    cosine similarity and Heron's formula

    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_20_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
     է
    0.44
     same
    0.44
     преимущественно
    0.41
     humor
    0.39
     в
    0.39
     authenticity
    0.39
     v
    0.38
     ourselves
    0.38
     even
    0.38
     ч
    0.38
    POSITIVE LOGITS
    𝙃
    0.52
     ಸಮಸ್ಯ
    0.50
    esistenza
    0.50
     ಪ್ರಕರಣ
    0.49
    žne
    0.47
    #}
    0.45
     વૃક્ષ
    0.45
    Bromo
    0.44
    телно
    0.44
    વવા
    0.44
    Activations Density 0.000%

    No Known Activations