© 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. 171685
    Prev
    Next
    INDEX
    Explanations

    looking for a

    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
     بالټ
    0.43
    }}=\
    0.42
     काउंसिल
    0.42
    াচার্য
    0.41
    ಇದ
    0.41
    परिवार
    0.41
    ertura
    0.40
     FormControl
    0.40
     Cert
    0.40
    என்ன
    0.40
    POSITIVE LOGITS
    하시오
    0.47
    ],
    0.45
     आणि
    0.44
     بنی
    0.43
    .]
    0.42
     ح
    0.42
    .].
    0.41
     biota
    0.40
     水
    0.40
     والم
    0.40
    Activations Density 0.000%

    No Known Activations