© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139639
    Prev
    Next
    INDEX
    Explanations

    1939-1945

    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_12_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
     HTMLSc
    0.50
    ,\\
    0.49
     Ư
    0.49
     로
    0.48
    Roi
    0.48
     θερ
    0.48
     }(\
    0.46
     Fleurit
    0.46
    统一
    0.46
    -\
    0.46
    POSITIVE LOGITS
     wants
    0.55
    Когда
    0.50
     drug
    0.50
     meaningless
    0.49
     périodes
    0.47
     dumping
    0.46
     reckons
    0.46
     government
    0.45
     terminology
    0.45
    ov
    0.45
    Activations Density 0.000%

    No Known Activations