© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99210
    Prev
    Next
    INDEX
    Explanations

    astonian

    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_16_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
    Robust
    0.54
    Re
    0.51
    Bo
    0.49
    </h3>
    0.49
    Games
    0.49
    お
    0.49
    Tur
    0.48
    Wel
    0.48
     =
    0.48
     Agile
    0.48
    POSITIVE LOGITS
    iť
    0.49
    aný
    0.44
     vendedor
    0.44
     stoneware
    0.44
    গ্রস্থ
    0.44
    uldades
    0.43
    ವಾಡ
    0.43
    ைகளையும்
    0.43
    ཋ
    0.43
    ভান
    0.43
    Activations Density 0.000%

    No Known Activations