© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205383
    Prev
    Next
    INDEX
    Explanations

    sodium intake

    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_25_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
     Blument
    0.42
    ക്കാര്‍
    0.40
    atomy
    0.40
     ನ
    0.38
    ၸ
    0.37
    нор
    0.36
     जल्
    0.35
     Norris
    0.35
     interi
    0.35
    forward
    0.34
    POSITIVE LOGITS
     రో
    0.43
     }+\
    0.40
     encuentro
    0.39
     encuentros
    0.39
    álního
    0.39
     }).
    0.38
    рё
    0.38
    keh
    0.37
    য়াল
    0.36
    Dimension
    0.36
    Activations Density 0.001%

    No Known Activations