© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 15715
    Prev
    Next
    INDEX
    Explanations

    George Washington, Pentagon, February

    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_34_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
    ‚
    0.38
    Fhir
    0.38
    IAN
    0.38
     元
    0.37
    Raise
    0.37
    ビル
    0.37
    Provision
    0.36
    icity
    0.36
    \,
    0.36
    :=
    0.36
    POSITIVE LOGITS
     Potomac
    0.59
    ಿಲ್ಲ
    0.44
     Fairfax
    0.41
     Prit
    0.38
     smoothly
    0.36
    Smo
    0.36
     Serena
    0.35
     perfected
    0.35
     decedent
    0.34
     കള
    0.33
    Activations Density 0.009%

    No Known Activations