© 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. 168397
    Prev
    Next
    INDEX
    Explanations

    topical or internal use

    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
     nail
    0.42
     bowl
    0.39
     coating
    0.38
     bowls
    0.37
    噴
    0.37
     pict
    0.37
    Xe
    0.37
     Nail
    0.36
     cuticle
    0.36
     bid
    0.36
    POSITIVE LOGITS
     sociis
    0.43
    Sov
    0.38
     synthesizing
    0.38
    िकुलम
    0.37
    ຫຼ
    0.37
    obbies
    0.36
    فاع
    0.36
    숏
    0.36
    ʑ
    0.36
    irtschaft
    0.35
    Activations Density 0.001%

    No Known Activations