© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13170
    Prev
    Next
    INDEX
    Explanations

    The neuron detects list-like separators

    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_13_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
    ES
    0.46
    AS
    0.41
    Es
    0.41
    AM
    0.40
    ED
    0.40
    The
    0.38
     novos
    0.38
    S
    0.37
    ET
    0.36
    As
    0.36
    POSITIVE LOGITS
    ränkt
    0.36
    irting
    0.36
    얗
    0.36
    igated
    0.35
    ubercul
    0.35
    funktion
    0.33
    äure
    0.33
    ubes
    0.33
    ventional
    0.32
    ᱗
    0.32
    Activations Density 0.016%

    No Known Activations