© 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. 10533
    Prev
    Next
    INDEX
    Explanations

    language encouraging someone to make contact and seek further information

    oai_token-act-pair · gemini-2.0-flash

    Business contact information

    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
    verwijspagina
    -0.81
    uxxxx
    -0.69
     coute
    -0.65
     beginnetje
    -0.63
     BoxFit
    -0.61
    ArgumentParser
    -0.59
     يتيمه
    -0.59
    DIPSETTING
    -0.59
     argint
    -0.59
     Grecs
    -0.58
    POSITIVE LOGITS
    ArrowToggle
    0.58
    compl
    0.47
     insu
    0.47
     raised
    0.47
    ="@+
    0.47
    QUOT
    0.47
     raising
    0.46
    ricus
    0.45
     midday
    0.44
     chased
    0.44
    Activations Density 3.276%

    No Known Activations