© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10646
    Prev
    Next
    INDEX
    Explanations

    DNA sequences and scientific notations including primers and probes.

    oai_token-act-pair · gemini-2.0-flash

    DNA sequences/primers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     K
    -0.69
     H
    -0.66
     E
    -0.58
     e
    -0.56
     R
    -0.53
     San
    -0.52
     N
    -0.52
     Base
    -0.52
     P
    -0.52
     base
    -0.51
    POSITIVE LOGITS
     myſelf
    1.28
     itſelf
    1.26
     ―――――
    1.22
     ་་
    1.16
     Jefus
    1.16
     Efq
    1.13
     Theſe
    1.09
     Anſ
    1.06
     Houſe
    1.05
    ſelves
    1.05
    Activations Density 2.981%

    No Known Activations