© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46075
    Prev
    Next
    INDEX
    Explanations

    long followed by something

    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_13_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
     Milliarden
    0.40
     composta
    0.38
     vijf
    0.37
     kucch
    0.37
     composto
    0.36
     ধূ
    0.36
     determinante
    0.36
    柏
    0.36
     composée
    0.36
    ichten
    0.35
    POSITIVE LOGITS
    м
    0.46
     be
    0.44
    .
    0.42
     award
    0.39
    (?
    0.38
    Allowed
    0.38
    ים
    0.37
     at
    0.37
    ссе
    0.37
    /
    0.36
    Activations Density 0.001%

    No Known Activations