© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17839
    Prev
    Next
    INDEX
    Explanations

    correct, incorrect, true, false

    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_34_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
    Ah
    0.41
    䁂
    0.41
    Less
    0.40
    Shaw
    0.40
    Suitable
    0.38
    Brom
    0.38
    Allah
    0.38
    Reduce
    0.37
    يجي
    0.37
     eroded
    0.37
    POSITIVE LOGITS
    ͅ
    0.40
     Kaise
    0.39
     ట్రా
    0.39
     completamente
    0.38
     HEAT
    0.37
    FRS
    0.37
     Trek
    0.36
     utterly
    0.36
     Sco
    0.35
     lectures
    0.35
    Activations Density 0.152%

    No Known Activations