© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4410
    Prev
    Next
    INDEX
    Explanations

    IDENTITY column creation

    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_39_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
    沨
    0.41
     yardım
    0.41
    oree
    0.37
    щении
    0.37
    lawn
    0.36
    เภ
    0.36
    NEEDED
    0.36
    脤
    0.36
    ầu
    0.36
    τι
    0.36
    POSITIVE LOGITS
     disabled
    0.47
     disable
    0.45
    disable
    0.43
     sausage
    0.40
    Disable
    0.40
     disables
    0.40
    Investors
    0.38
     Disable
    0.38
    Disabled
    0.38
    disabled
    0.37
    Activations Density 0.005%

    No Known Activations