© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167742
    Prev
    Next
    INDEX
    Explanations

    types of rocks

    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_56_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
    stone
    0.58
    stones
    0.57
    town
    0.47
    garden
    0.46
    hower
    0.41
    石
    0.41
     sh
    0.39
    boxes
    0.39
     Volker
    0.38
    garten
    0.38
    POSITIVE LOGITS
     ic
    0.43
    ρευ
    0.40
    மானிய
    0.38
    蓊
    0.37
    INDOW
    0.36
     آب
    0.36
    ineed
    0.35
    顧問
    0.35
    icher
    0.35
     deteriorate
    0.35
    Activations Density 0.003%

    No Known Activations