© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9092
    Prev
    Next
    INDEX
    Explanations

    IP address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     clothing
    0.18
     food
    0.18
     garment
    0.18
    M
    0.18
    ativity
    0.17
     थोड़ी
    0.17
    ener
    0.17
    arrow
    0.17
     जाट
    0.17
    energy
    0.16
    POSITIVE LOGITS
     conoscenza
    0.19
     hton
    0.18
     densément
    0.18
    𝒔
    0.18
     Governorate
    0.18
     assin
    0.17
    <unused2140>
    0.17
     reprehenderit
    0.17
     TMN
    0.17
    迩
    0.16
    Activations Density 0.013%

    No Known Activations