© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211443
    Prev
    Next
    INDEX
    Explanations

    access to dataset

    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_20_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
    iga
    0.44
    C
    0.43
    se
    0.43
    vat
    0.43
    art
    0.42
    ]"
    0.42
    ber
    0.41
    kn
    0.41
    "
    0.41
     عرف
    0.40
    POSITIVE LOGITS
    蘋
    0.44
    भरा
    0.41
     silahkan
    0.41
     pohod
    0.41
    ారణ
    0.41
     elapse
    0.40
     spool
    0.40
     confuse
    0.39
    Ⴌ
    0.39
     pdelay
    0.39
    Activations Density 0.000%

    No Known Activations