© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116887
    Prev
    Next
    INDEX
    Explanations

    welcome and learn

    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_27_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
    comstock
    0.43
    rivastava
    0.41
    ➳
    0.41
    ∈</
    0.40
    Mình
    0.39
     Víctor
    0.38
    POSITORY
    0.38
    𝟮
    0.38
     ConcurrentTask
    0.38
    ствима
    0.38
    POSITIVE LOGITS
     desire
    0.40
     viewing
    0.37
     butcher
    0.36
     sighting
    0.36
     marc
    0.34
     camera
    0.34
     camer
    0.34
     textual
    0.34
     push
    0.33
     handwriting
    0.33
    Activations Density 0.000%

    No Known Activations