© 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. 12849
    Prev
    Next
    INDEX
    Explanations

    various parts of computer code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     and
    -0.59
     (
    -0.53
     “
    -0.47
    -0.45
     or
    -0.42
    :”
    -0.41
    :
    -0.41
    </strong>
    -0.40
     to
    -0.40
    “
    -0.39
    POSITIVE LOGITS
     ainfi
    0.94
     stället
    0.93
     avoient
    0.90
     purpoſe
    0.88
     mauvaises
    0.88
    دانشنامهٔ
    0.88
     iſt
    0.87
     Monfieur
    0.86
    Personendaten
    0.86
     plufieurs
    0.85
    Activations Density 38.030%
    No Known Activations