© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48991
    Prev
    Next
    INDEX
    Explanations

    several or few

    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
    有两种
    0.41
    atform
    0.37
    랜
    0.37
    heh
    0.36
    嫉
    0.36
    emia
    0.35
    adek
    0.35
    টেও
    0.35
    ከል
    0.35
    вел
    0.34
    POSITIVE LOGITS
    几
    2.17
    幾
    2.02
     several
    1.95
     несколько
    1.93
     몇
    1.92
     چند
    1.85
    几个
    1.84
    several
    1.84
     beberapa
    1.81
     kilka
    1.80
    Activations Density 0.000%

    No Known Activations