© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11466
    Prev
    Next
    INDEX
    Explanations

    various separators, links, categories and metadata, including numbers and other numerical quantities like dates and times.

    oai_token-act-pair · gemini-2.0-flash

    wikipedia references sections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    -0.72
     Diſ
    -0.70
     Efq
    -0.69
     Jefus
    -0.66
     Beſ
    -0.65
     Houſe
    -0.65
     Majefty
    -0.65
     Monfieur
    -0.65
     ―――――
    -0.63
     pleaſure
    -0.62
    POSITIVE LOGITS
    şiv
    0.56
    ANSA
    0.55
    fa
    0.55
     Roskov
    0.54
    Geplaatst
    0.52
    fjspx
    0.52
    INSEE
    0.50
    Portale
    0.49
    Personensuche
    0.49
     typelib
    0.48
    Activations Density 3.381%

    No Known Activations