© 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. 5715
    Prev
    Next
    INDEX
    Explanations

    a mix of related things (1) medical/biological terms (2) the names of things that manage persistence. (3) words that mean "related"

    oai_token-act-pair · gemini-2.0-flash

    say "p" 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
     Պ
    -0.56
     Pos
    -0.47
    logeny
    -0.46
    acles
    -0.45
     Pan
    -0.44
    ometric
    -0.44
     П
    -0.44
     Prop
    -0.43
     Pom
    -0.43
     Pose
    -0.43
    POSITIVE LOGITS
     pn
    0.68
    pp
    0.68
     p
    0.65
     pp
    0.64
     pe
    0.64
     pi
    0.63
    pname
    0.60
    pppp
    0.60
    ppp
    0.59
     pname
    0.58
    Activations Density 23.727%

    No Known Activations