© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16101
    Prev
    Next
    INDEX
    Explanations

    apostrophes followed by certain letters.

    oai_token-act-pair · gemini-2.0-flash

    Apostrophes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Theſe
    -1.13
     chofe
    -1.10
     Reſ
    -1.05
     purpoſe
    -1.05
     myſelf
    -1.04
     raiſ
    -1.04
     &___
    -1.04
     himſelf
    -1.03
     ſhould
    -1.03
    <bos>
    -1.03
    POSITIVE LOGITS
    M
    0.26
     a
    0.21
    De
    0.17
    DA
    0.16
    DatabaseError
    0.15
     م
    0.14
    CHE
    0.14
     M
    0.14
     nebo
    0.14
    templateUrl
    0.13
    Activations Density 4.951%

    No Known Activations