© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210334
    Prev
    Next
    INDEX
    Explanations

    explanation follows

    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
     потім
    0.41
    以后
    0.40
    以後
    0.38
    ッター
    0.38
     kasnije
    0.36
     nv
    0.35
    豸
    0.35
    гай
    0.35
    🥕
    0.35
     मैथमेट
    0.34
    POSITIVE LOGITS
     allow
    0.49
    Allow
    0.44
     Allow
    0.43
     enriqu
    0.42
     en
    0.42
     Pays
    0.41
     allant
    0.40
     Celsius
    0.39
     En
    0.39
     Di
    0.38
    Activations Density 0.000%

    No Known Activations