© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212684
    Prev
    Next
    INDEX
    Explanations

    legal or criminal context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     charges
    0.43
     charge
    0.42
     chargés
    0.41
     charged
    0.40
     chargé
    0.39
    𝗻
    0.39
     adverse
    0.38
     suffixes
    0.37
     कॉर्
    0.37
     Fabrication
    0.37
    POSITIVE LOGITS
    hex
    0.46
    执
    0.37
    ListAdapter
    0.36
    執
    0.35
    esseract
    0.35
     fahren
    0.34
    佅
    0.34
     দ
    0.34
    hythm
    0.34
    แรง
    0.33
    Activations Density 0.000%

    No Known Activations