© 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. 134394
    Prev
    Next
    INDEX
    Explanations

    signal-to-noise ratio (SNR)

    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
    ية
    1.04
    ně
    0.94
    ة
    0.92
    承诺
    0.91
    prnewswire
    0.90
    ితే
    0.89
    أن
    0.89
    }/>
    0.86
    c
    0.86
    b
    0.86
    POSITIVE LOGITS
     you
    1.27
    -
    1.24
    :
    0.99
     vous
    0.98
    ,
    0.98
    ות
    0.94
    –
    0.94
    -"
    0.91
     can
    0.90
    の間
    0.90
    Activations Density 0.000%

    No Known Activations