© 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. 35862
    Prev
    Next
    INDEX
    Explanations

    tùy thuộc vào

    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
    enamefont
    0.74
    هم
    0.69
    manifolds
    0.68
    ა
    0.68
    по
    0.67
    HA
    0.67
     باقی
    0.67
    のは
    0.66
    ஸ்
    0.64
    וס
    0.64
    POSITIVE LOGITS
    )，
    0.65
     t
    0.62
    ),
    0.62
     Siege
    0.60
    <0x91>
    0.60
     are
    0.59
     än
    0.59
     scallop
    0.59
    nict
    0.58
     archaeologist
    0.58
    Activations Density 0.000%

    No Known Activations