© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50617
    Prev
    Next
    INDEX
    Explanations

    programming concepts

    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_55_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
     supported
    0.46
     Supports
    0.42
    |$.
    0.42
     Supported
    0.41
     Julian
    0.39
     supports
    0.38
     necessarily
    0.38
    Supported
    0.38
     nhu
    0.38
     tên
    0.38
    POSITIVE LOGITS
     connections
    0.38
    DECL
    0.38
     installations
    0.36
     decrement
    0.35
    )}
    0.34
    Connections
    0.34
    ruik
    0.34
    chemy
    0.34
    宣言
    0.33
    য়েড
    0.33
    Activations Density 0.032%

    No Known Activations