© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175577
    Prev
    Next
    INDEX
    Explanations

    height

    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
     Жа
    0.41
     rem
    0.39
     original
    0.39
     subsidence
    0.39
     reverts
    0.38
     mr
    0.37
    ↵↵↵↵↵↵↵↵↵↵
    0.37
     delirium
    0.37
     revert
    0.36
     blackout
    0.36
    POSITIVE LOGITS
    🐲
    0.43
    ភ្
    0.40
    €
    0.39
    peliculas
    0.38
    ishments
    0.38
    🐬
    0.38
    <0x06>
    0.37
     تدخل
    0.37
    练
    0.37
     कोशिश
    0.37
    Activations Density 0.001%

    No Known Activations