© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206266
    Prev
    Next
    INDEX
    Explanations

    each followed by unit or item

    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_6_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
    '
    1.02
    the
    1.00
    (
    1.00
     timeline
    0.93
     gunung
    0.91
     shoreline
    0.88
     stream
    0.88
     pomegranate
    0.87
     projection
    0.86
    0
    0.86
    POSITIVE LOGITS
    és
    1.20
    ors
    1.16
     effectuer
    1.15
    ك
    1.11
     факти
    1.06
     Duits
    1.06
     tohoto
    1.03
    كس
    1.02
    ított
    1.02
     вось
    1.02
    Activations Density 0.010%

    No Known Activations