© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125968
    Prev
    Next
    INDEX
    Explanations

    sheep and lambs

    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_37_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
     cents
    0.38
    elink
    0.37
    禮
    0.36
    ానిక
    0.36
    athing
    0.36
    eding
    0.35
    礼
    0.35
     anlam
    0.35
    pinterest
    0.34
    꾹
    0.34
    POSITIVE LOGITS
     Lamb
    0.48
    Sheep
    0.46
     Sheep
    0.44
    羊
    0.42
     lamb
    0.41
     alleg
    0.40
     sheep
    0.40
    sheep
    0.39
     Silence
    0.39
     lambs
    0.38
    Activations Density 0.000%

    No Known Activations