© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14209
    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_34_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
     Theoret
    0.42
    Ball
    0.42
     mág
    0.38
     Ball
    0.37
    球
    0.37
     théor
    0.36
    Balls
    0.36
     theoret
    0.36
    ContextProvider
    0.36
    jaa
    0.35
    POSITIVE LOGITS
    보니
    0.40
    ตน
    0.38
     உயரம்
    0.37
    Subs
    0.36
    pmatrix
    0.35
    适
    0.35
     Datuk
    0.35
     अति
    0.34
     kotak
    0.34
     sundry
    0.34
    Activations Density 0.000%

    No Known Activations