© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13184
    Prev
    Next
    INDEX
    Explanations

    strings of characters that might be names or ids or codes

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
    spesies
    -0.75
    ValueStyle
    -0.63
     AssemblyTitle
    -0.63
    gants
    -0.62
     nakalista
    -0.61
    onomía
    -0.60
    //
    -0.60
     Theſe
    -0.60
     صوتيه
    -0.59
    +#+
    -0.58
    POSITIVE LOGITS
     de
    0.49
    семь
    0.47
    TableBody
    0.42
    imler
    0.41
     galería
    0.41
     ac
    0.40
     pon
    0.40
     con
    0.39
     interior
    0.38
    hå
    0.38
    Activations Density 0.176%

    No Known Activations