© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206559
    Prev
    Next
    INDEX
    Explanations

    Grim

    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_56_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
     facial
    0.40
    𝒞
    0.40
    מיד
    0.40
     accounts
    0.39
     Accounts
    0.39
     Faces
    0.39
     Qxf
    0.39
     admit
    0.38
    aschen
    0.38
     Facial
    0.38
    POSITIVE LOGITS
    ewall
    0.41
    ক্তি
    0.40
    及
    0.40
    angolo
    0.38
    Developing
    0.38
    ding
    0.35
     第一
    0.35
    ebox
    0.35
    Lucky
    0.35
    बल
    0.35
    Activations Density 0.000%

    No Known Activations