© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150426
    Prev
    Next
    INDEX
    Explanations

    dish types

    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_23_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
     όχι
    0.38
    mitter
    0.38
    <unused561>
    0.37
    κού
    0.36
    պես
    0.36
     "..
    0.36
     Institutions
    0.36
     учреждений
    0.36
    콰
    0.35
     সহজে
    0.35
    POSITIVE LOGITS
     gcd
    0.42
    Pays
    0.42
    御座
    0.42
     earths
    0.41
     declines
    0.39
    eyer
    0.37
    Fresh
    0.37
     forceps
    0.36
     gk
    0.36
     pays
    0.36
    Activations Density 0.010%

    No Known Activations