© 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. 92012
    Prev
    Next
    INDEX
    Explanations

    folk songs or ballads

    np_acts-logits-general · gemini-2.5-flash-lite

    folk music

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    words related to social and political awareness.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    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
    TikTok
    0.55
    رف
    0.53
    锜
    0.49
     TikTok
    0.46
    煒
    0.44
    铖
    0.44
    >∕
    0.44
    窣
    0.42
    Bark
    0.42
    ೋಜನ
    0.41
    POSITIVE LOGITS
    wine
    0.54
    aan
    0.54
     irresist
    0.53
     Pendant
    0.53
    0.53
     equaling
    0.52
    იზ
    0.51
    ιου
    0.49
    ̉i
    0.49
     দেবতাদের
    0.48
    Activations Density 0.007%

    No Known Activations