© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11287
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    precedes verbs

    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
    IndentedString
    -0.60
    ########.
    -0.58
    smithy
    -0.57
     تضيفلها
    -0.56
    ignano
    -0.55
    RegressionTest
    -0.53
    tagext
    -0.52
    intios
    -0.52
    getExtras
    -0.52
    LookAnd
    -0.51
    POSITIVE LOGITS
    สบ
    0.48
    ậc
    0.47
     möjligt
    0.47
    "]);
    0.44
    TagMode
    0.44
     Roskov
    0.44
    CloseOperation
    0.43
    ]));
    0.41
     Schnitt
    0.41
     silence
    0.41
    Activations Density 4.090%

    No Known Activations