© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120833
    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_27_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
     getText
    0.41
     ইসলামের
    0.38
     szö
    0.38
    劭
    0.38
    OLYBD
    0.38
     getDefault
    0.37
    ucose
    0.37
     "????.??.??"]
    0.36
    スキ
    0.36
    URED
    0.36
    POSITIVE LOGITS
    also
    0.37
    core
    0.36
    Unique
    0.35
    fila
    0.34
    latest
    0.33
     opening
    0.33
     practically
    0.33
     Opening
    0.33
    own
    0.33
     kira
    0.33
    Activations Density 0.000%

    No Known Activations