© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131609
    Prev
    Next
    INDEX
    Explanations

    medical

    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_50_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
     Fitzpatrick
    0.39
     screams
    0.37
    ᆫ
    0.37
    댄
    0.36
     screaming
    0.36
     Sweeney
    0.36
    ലൈ
    0.35
    redir
    0.35
    skom
    0.35
     scream
    0.34
    POSITIVE LOGITS
     AKS
    0.43
     कैसा
    0.41
     ال
    0.40
    perature
    0.40
    ருக
    0.40
    Su
    0.38
     D
    0.38
    अफ
    0.38
     andro
    0.38
    鹵
    0.37
    Activations Density 0.000%

    No Known Activations