© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3855
    Prev
    Next
    INDEX
    Explanations

    Frederick Douglass and abolition

    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_40_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
     Bars
    0.43
     Ripley
    0.39
     Brant
    0.39
    mail
    0.38
    Bars
    0.37
    Dots
    0.37
     ";
    0.36
     وسی
    0.36
    胚
    0.36
     mail
    0.35
    POSITIVE LOGITS
     Frederick
    0.41
    predicate
    0.41
    Frederick
    0.40
     predicate
    0.39
     slave
    0.38
     fugitive
    0.38
     нар
    0.38
    रुण
    0.37
    𝐔
    0.37
    баев
    0.36
    Activations Density 0.015%

    No Known Activations