© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6580
    Prev
    Next
    INDEX
    Explanations

    positive sentiment classifier

    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_39_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
     both
    0.47
    男女
    0.47
    上下
    0.46
    both
    0.44
     উভয়
    0.43
    両
    0.43
     दोनों
    0.41
     BOTH
    0.40
     دونوں
    0.40
     både
    0.40
    POSITIVE LOGITS
     HOR
    0.37
    inode
    0.37
     করেনি
    0.35
    esModule
    0.34
    லான
    0.34
    𝑋
    0.34
    nep
    0.34
     denominator
    0.34
    ोग्राम
    0.34
     On
    0.34
    Activations Density 0.520%

    No Known Activations