© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9500
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that indicate quality, quantity, or emotion

    oai_token-act-pair · gemini-2.0-flash

    positive sentiment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])):
    -0.58
    DockStyle
    -0.55
    keyColumn
    -0.53
    oredCriteria
    -0.52
    annica
    -0.47
    ']?>
    -0.46
    ()));
    -0.46
    AndEndTag
    -0.45
    migrationBuilder
    -0.45
     metade
    -0.44
    POSITIVE LOGITS
    setAccessible
    0.63
    +#+#
    0.62
     Familienname
    0.60
    onomía
    0.60
     مشين
    0.57
     跳转至
    0.56
    ifikationer
    0.53
    omorphism
    0.52
    IBarButtonItem
    0.51
    Élet
    0.51
    Activations Density 2.948%

    No Known Activations