© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 130871
    Prev
    Next
    INDEX
    Explanations

    css properties

    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_25_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
     reminiscent
    0.42
     no
    0.41
     similar
    0.40
     invers
    0.38
     sans
    0.37
     guilty
    0.37
     축
    0.36
     clueless
    0.36
     sparkly
    0.36
     null
    0.35
    POSITIVE LOGITS
    孩
    0.42
    Sibling
    0.39
     ਸਿੰ
    0.39
     হইয়৷
    0.39
     tây
    0.39
    ValueSet
    0.38
    也會
    0.38
     পাবেন
    0.38
    菟
    0.38
     Collectively
    0.37
    Activations Density 0.002%

    No Known Activations