© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37918
    Prev
    Next
    INDEX
    Explanations

    anchor point text

    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_3_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
    ვალ
    0.61
    อยู่ที่
    0.60
     нажмите
    0.59
     нажа
    0.57
    K
    0.56
     bare
    0.56
     heartbreak
    0.56
    herlands
    0.55
    فاع
    0.55
    ס
    0.55
    POSITIVE LOGITS
    j
    0.77
     anch
    0.68
    Anchor
    0.68
     Anchor
    0.68
    t
    0.68
    m
    0.67
     anchors
    0.66
    ,\"
    0.65
     anchored
    0.64
     anchorage
    0.64
    Activations Density 0.000%

    No Known Activations