© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8890
    Prev
    Next
    INDEX
    Explanations

    places, things or people being named

    oai_token-act-pair · gemini-2.0-flash

    named or modeled

    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
    +#+
    -0.47
    aré
    -0.44
     unpublished
    -0.44
    Hô
    -0.42
    ילו
    -0.42
    κρι
    -0.42
    detta
    -0.42
    ApiProperty
    -0.42
    𝐪
    -0.41
    δος
    -0.40
    POSITIVE LOGITS
     after
    2.53
    after
    2.28
    After
    1.94
     After
    1.94
     dopo
    1.86
     após
    1.85
     setelah
    1.84
     после
    1.81
     після
    1.80
     après
    1.73
    Activations Density 2.901%

    No Known Activations