© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150517
    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_60_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
    HRIM
    0.44
    řich
    0.42
    áreas
    0.42
    á
    0.39
    appings
    0.39
    হারে
    0.38
    𝘽
    0.38
    ELDS
    0.38
    RxDocument
    0.38
     पदार्
    0.38
    POSITIVE LOGITS
     aus
    0.64
     из
    0.56
     uit
    0.55
     z
    0.46
     iz
    0.46
    いた
    0.45
     Econom
    0.41
     out
    0.41
    on
    0.41
     із
    0.41
    Activations Density 0.000%

    No Known Activations