© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3602
    Prev
    Next
    INDEX
    Explanations

    code syntax and symbols with a slight preference for the keyword "Configuration".

    oai_token-act-pair · gemini-2.0-flash

    len

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Theſe
    -0.78
    !")
    -0.63
     Diſ
    -0.63
     Beſ
    -0.63
     '',
    -0.60
     "",
    -0.60
     [],
    -0.57
     ་་
    -0.57
    abestanden
    -0.56
     Anſ
    -0.56
    POSITIVE LOGITS
    ثيق
    0.63
     secundario
    0.60
    umbra
    0.58
    naphthal
    0.57
    RIAGE
    0.57
    umers
    0.57
    stücke
    0.57
     Estadística
    0.57
    taxia
    0.57
    ension
    0.56
    Activations Density 0.476%

    No Known Activations