© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1868
    Prev
    Next
    INDEX
    Explanations

    followed by if

    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_39_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
    驃
    0.41
    chloride
    0.37
    Петер
    0.37
     pointless
    0.36
    pios
    0.36
     vagu
    0.35
    衹
    0.34
     밀
    0.34
     polít
    0.34
    絘
    0.33
    POSITIVE LOGITS
    ➢
    0.40
     False
    0.38
    ➨
    0.38
    ➡️
    0.37
    atian
    0.36
    arena
    0.35
     FALSE
    0.35
     Marina
    0.35
    rijke
    0.34
     siku
    0.34
    Activations Density 0.043%

    No Known Activations