© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6121
    Prev
    Next
    INDEX
    Explanations

    all to

    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
    ందో
    0.39
    之为
    0.38
     arbej
    0.36
     <<-
    0.35
    സും
    0.35
    ggbb
    0.35
     казни
    0.35
    éu
    0.34
     開
    0.34
    zugs
    0.34
    POSITIVE LOGITS
     else
    0.41
    真正的
    0.38
    assam
    0.37
     मोहो
    0.35
    Lovely
    0.35
     अम्
    0.35
    ார்க்க
    0.35
    φέρον
    0.34
     Else
    0.33
     ELSE
    0.33
    Activations Density 0.035%

    No Known Activations