© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92039
    Prev
    Next
    INDEX
    Explanations

    InstanceState followed by ) or :

    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_11_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
     elektronic
    0.51
    क्षण
    0.50
    ผ่าน
    0.50
     passcode
    0.50
     protons
    0.50
    ?
    0.49
     cathodic
    0.49
    :
    0.48
    خیص
    0.47
     passivation
    0.46
    POSITIVE LOGITS
    st
    0.60
    promised
    0.57
    us
    0.55
    ah
    0.54
    <0x80>
    0.53
    attiyam
    0.52
    tapping
    0.52
    havam
    0.52
    нія
    0.51
    phabet
    0.50
    Activations Density 0.000%

    No Known Activations