© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175767
    Prev
    Next
    INDEX
    Explanations

    mediating variables

    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_20_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
    ocam
    0.47
     når
    0.46
     বিবাহ
    0.45
     när
    0.44
     বিবাহের
    0.44
    禕
    0.44
    ازه
    0.43
    róleo
    0.42
    aneo
    0.42
    ühle
    0.41
    POSITIVE LOGITS
    .)
    0.46
    )
    0.45
    விடும்
    0.44
     Kramer
    0.44
     Fre
    0.44
     )
    0.43
     poor
    0.43
     FRP
    0.43
    似的
    0.43
     foolish
    0.42
    Activations Density 0.000%

    No Known Activations