© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36419
    Prev
    Next
    INDEX
    Explanations

    reach

    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
    in
    1.09
    et
    0.99
    0
    0.91
    <0x80>
    0.86
    t
    0.81
    inium
    0.79
    an
    0.73
    inę
    0.73
    ihe
    0.69
     bahwa
    0.68
    POSITIVE LOGITS
     to
    0.78
     نے
    0.77
     REACH
    0.72
    $.
    0.70
     remnants
    0.68
     countertops
    0.68
     redshift
    0.67
    ፁ
    0.66
     frantic
    0.65
     punishing
    0.65
    Activations Density 0.035%

    No Known Activations