© 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. 3134
    Prev
    Next
    INDEX
    Explanations

    grammatical constructs such as "either...or" and "as a"

    oai_token-act-pair · gemini-2.0-flash

    option

    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
     mergeFrom
    -0.53
     emplois
    -0.51
    ########.
    -0.50
    RenderAtEndOf
    -0.50
    сылкі
    -0.50
    CPtr
    -0.47
    ёв
    -0.46
     indépendante
    -0.46
    jooq
    -0.45
     gynhyrchwyd
    -0.45
    POSITIVE LOGITS
     option
    1.22
     Option
    1.12
     options
    1.12
    Option
    1.09
    option
    1.08
     optional
    1.07
    オプション
    1.04
    opcional
    1.02
     OPTION
    1.01
     Options
    0.99
    Activations Density 0.850%

    No Known Activations