© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43427
    Prev
    Next
    INDEX
    Explanations

    type of data after bracket

    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_22_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
     z
    0.38
    Over
    0.37
     |
    0.33
    B
    0.33
    Prol
    0.32
     அ
    0.32
    :
    0.32
     :
    0.31
     hard
    0.31
     aise
    0.31
    POSITIVE LOGITS
    ুগত্য
    0.38
    ிலி
    0.38
    लिब्र
    0.37
     opcao
    0.37
     ublox
    0.37
     clickView
    0.36
    ുകളില്‍
    0.35
    ির্ব
    0.35
    UpdateChoice
    0.34
     Yesu
    0.34
    Activations Density 0.004%

    No Known Activations