© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140693
    Prev
    Next
    INDEX
    Explanations

    clay masks and thermal paste

    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_12_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
    Saturday
    0.14
    6
    0.13
    Pentru
    0.12
    4
    0.12
    Prés
    0.12
    Karen
    0.11
    ۔
    0.11
    ።
    0.11
    ขนาด
    0.11
    semibold
    0.11
    POSITIVE LOGITS
     acuerdos
    0.14
    hes
    0.13
     строк
    0.12
     đỡ
    0.12
     edificios
    0.12
     llor
    0.12
     subsidi
    0.11
     dispuesto
    0.11
    VENT
    0.11
     Vent
    0.11
    Activations Density 0.000%

    No Known Activations