© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59257
    Prev
    Next
    INDEX
    Explanations

    Ron

    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_2_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
    0
    1.63
    im
    1.14
    arif
    1.10
    arap
    1.09
    ر
    1.05
    ר
    1.05
    ar
    1.03
    arne
    1.02
    ار
    1.01
    رین
    1.01
    POSITIVE LOGITS
     on
    1.80
    </h4>
    1.10
    </h1>
    1.08
     uma
    1.08
     empezar
    1.06
     ON
    1.05
    :"",
    1.03
     acuerdo
    1.01
    "،
    1.01
     allemand
    1.01
    Activations Density 0.000%

    No Known Activations