© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12521
    Prev
    Next
    INDEX
    Explanations

    expressed sentiment or emotion

    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
    oretical
    0.53
    éricos
    0.53
    kę
    0.53
    Iraq
    0.52
    R
    0.52
     खाता
    0.51
    OLOGICAL
    0.50
    urbo
    0.50
    उ
    0.50
    áže
    0.50
    POSITIVE LOGITS
     Sina
    0.57
     pla
    0.54
     geld
    0.53
     prema
    0.53
     gelt
    0.51
     tokens
    0.50
     neun
    0.50
     forti
    0.50
     Sebastian
    0.49
    лен
    0.49
    Activations Density 0.006%

    No Known Activations