© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31599
    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_31_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
    spel
    0.42
    Spin
    0.41
    Fifty
    0.39
    Ί
    0.38
    Call
    0.37
    Ask
    0.37
    Mult
    0.37
    Medical
    0.36
     Fifty
    0.36
    symplectic
    0.36
    POSITIVE LOGITS
     та
    0.39
    능
    0.36
     sorrow
    0.35
     tem
    0.35
     tpr
    0.35
     दस
    0.35
     девя
    0.34
    osa
    0.34
     tá
    0.34
     usa
    0.34
    Activations Density 0.000%

    No Known Activations