© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 106029
    Prev
    Next
    INDEX
    Explanations

    June

    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_44_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
    莼
    0.46
    ietta
    0.40
    odrome
    0.40
    कोल
    0.39
    千年
    0.39
     EMU
    0.38
     твор
    0.38
    ➰
    0.38
    దన
    0.38
     substr
    0.38
    POSITIVE LOGITS
    ToJava
    0.42
    nearest
    0.40
     sierpnia
    0.38
     rings
    0.37
     Bih
    0.35
     अलविदा
    0.34
     tł
    0.34
    seven
    0.34
    venuti
    0.34
    Atomic
    0.34
    Activations Density 0.001%

    No Known Activations