© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205935
    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_46_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
    Candidates
    0.44
    譎
    0.43
     elementi
    0.42
     مارت
    0.41
     Kirkpatrick
    0.40
     Candidates
    0.39
     candidatos
    0.39
     elemento
    0.39
    觡
    0.39
    zey
    0.39
    POSITIVE LOGITS
     War
    0.43
     वार
    0.40
     variance
    0.38
    War
    0.38
     чём
    0.37
     Variance
    0.37
     Events
    0.36
    events
    0.36
     what
    0.35
    wars
    0.35
    Activations Density 0.000%

    No Known Activations