© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261135
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
    Builder
    0.44
    ко
    0.43
    м
    0.41
    বাহ
    0.40
    芨
    0.40
     التد
    0.39
    зме
    0.39
     Builds
    0.39
    ર
    0.39
    Mystery
    0.39
    POSITIVE LOGITS
     pasal
    0.50
    ोजन
    0.49
     incriminating
    0.49
     いたし
    0.47
     forceps
    0.46
    onas
    0.46
     conscient
    0.46
     cuestion
    0.46
     ентите
    0.46
     manifold
    0.46
    Activations Density 0.000%

    No Known Activations