© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12099
    Prev
    Next
    INDEX
    Explanations

    words containing letter combinations like "res", "ies", "annex" or "fluo"

    oai_token-act-pair · gemini-2.0-flash

    "ci"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ########.
    -0.52
    Hentet
    -0.49
    AppCompatTheme
    -0.48
    CHAS
    -0.48
    FieldBuilder
    -0.48
    hard
    -0.47
    spir
    -0.47
     sy
    -0.47
    bited
    -0.47
     Carab
    -0.46
    POSITIVE LOGITS
    cie
    0.65
    ci
    0.65
    IsPostBack
    0.61
    cière
    0.59
    ciate
    0.59
    ciale
    0.59
    ciar
    0.57
    ciales
    0.57
    cia
    0.56
     hefyd
    0.56
    Activations Density 4.211%

    No Known Activations