© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151329
    Prev
    Next
    INDEX
    Explanations

    AI prompts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     Left
    0.40
    左
    0.39
     :
    0.39
     Ordinary
    0.39
     單
    0.38
     Tax
    0.38
     chel
    0.38
    –
    0.38
     Wrong
    0.38
     )),
    0.38
    POSITIVE LOGITS
    una
    0.59
     una
    0.58
    Sharp
    0.55
    E
    0.53
    Una
    0.50
    Uma
    0.48
     uma
    0.48
    must
    0.48
    Eine
    0.47
    eine
    0.46
    Activations Density 0.000%

    No Known Activations