© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117959
    Prev
    Next
    INDEX
    Explanations

    i'm here to listen

    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_27_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
     Fires
    0.37
     õ
    0.36
     beforeDir
    0.35
     suicide
    0.34
    гули
    0.34
     self
    0.33
     ban
    0.32
     suic
    0.32
     kop
    0.32
     قابل
    0.32
    POSITIVE LOGITS
    Vega
    0.34
     निच
    0.33
    Xbox
    0.33
    Arkansas
    0.33
    Chevrolet
    0.32
    ക്ടര്‍
    0.32
    젓
    0.32
    ጺ
    0.32
    sounding
    0.32
    Eddie
    0.32
    Activations Density 0.004%

    No Known Activations