© 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
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51915
    Prev
    Next
    INDEX
    Explanations

    true false

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    ➀
    0.46
     التاس
    0.45
    ❶
    0.44
     одном
    0.43
     eighteenth
    0.40
    一つ
    0.39
    第壹百
    0.39
     headroom
    0.38
    卅
    0.38
    тыми
    0.38
    POSITIVE LOGITS
     critiques
    0.47
    bool
    0.43
    FALSE
    0.42
     critique
    0.42
     Critic
    0.41
    STRONG
    0.41
    OUTPUT
    0.41
    łac
    0.41
    false
    0.40
    true
    0.40
    Activations Density 0.005%

    No Known Activations