© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59688
    Prev
    Next
    INDEX
    Explanations

    similarity, likeness, comparison

    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_11_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
     be
    0.74
     blatant
    0.59
    ל
    0.57
    ן
    0.55
     ק
    0.53
    breath
    0.51
     μέ
    0.51
    𝑘
    0.50
     k
    0.50
    كم
    0.50
    POSITIVE LOGITS
    ÂN
    0.66
    EN
    0.65
    ERS
    0.63
    }|=
    0.63
    ﾞ
    0.60
     seus
    0.59
    jz
    0.59
    Ни
    0.58
    Tôi
    0.58
    PER
    0.58
    Activations Density 0.009%

    No Known Activations