© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247099
    Prev
    Next
    INDEX
    Explanations

    assess continuous

    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_40_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
     মেডিক্যাল
    0.47
     Medical
    0.40
     Southeastern
    0.40
     SSI
    0.40
    醫
    0.40
     پزش
    0.39
     Kün
    0.38
    ⊷
    0.38
     physicians
    0.38
     एसएस
    0.37
    POSITIVE LOGITS
    continuous
    0.49
    Continuous
    0.47
     continuous
    0.47
     Continuous
    0.43
    CX
    0.42
     pint
    0.42
    𝔞
    0.42
    连续
    0.41
     sürekli
    0.41
     Pint
    0.40
    Activations Density 0.004%

    No Known Activations