© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179399
    Prev
    Next
    INDEX
    Explanations

    below a certain cutoff frequency

    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_24_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
    𠃊
    0.44
    olai
    0.42
     вулка
    0.42
    ர்வ
    0.42
    ántico
    0.42
    ría
    0.42
    Các
    0.41
    ㄒ
    0.41
    ભ્ય
    0.40
     फक्त
    0.40
    POSITIVE LOGITS
     McConnell
    0.40
    uri
    0.39
     سمیت
    0.38
    رحبا
    0.38
     arşivlendi
    0.38
    峭
    0.37
     liitty
    0.37
     nagy
    0.37
     layering
    0.36
     '
    0.35
    Activations Density 0.000%

    No Known Activations