© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6440
    Prev
    Next
    INDEX
    Explanations

    english stop words and punctuation contained within sentences

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    —
    -0.54
     (
    -0.49
    –
    -0.44
    ry
    -0.42
     arv
    -0.40
    --
    -0.39
    ()]
    -0.39
    -(
    -0.39
    ε
    -0.39
    бой
    -0.38
    POSITIVE LOGITS
    writeFieldEnd
    0.92
     lenker
    0.88
    AndEndTag
    0.85
    StructEnd
    0.83
     Efq
    0.82
    rungsseite
    0.81
     isInitialized
    0.81
    AutoScaleMode
    0.80
    TemporalType
    0.78
     RouterModule
    0.77
    Activations Density 2.051%

    No Known Activations