© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7201
    Prev
    Next
    INDEX
    Explanations

    the prefix "pre"

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'pre'

    np_token-act-pair-logits · gpt-4o-mini

    pre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     invokingState
    -0.58
    erschied
    -0.54
    تفصیلات
    -0.54
    JNIEnv
    -0.53
    #+#
    -0.52
    @[+][
    -0.51
    CreateModel
    -0.51
     colonias
    -0.48
    shadowRadius
    -0.48
     szabad
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.62
    Rhestr
    0.59
    Xna
    0.58
    OGND
    0.54
     pandemic
    0.54
     quam
    0.53
    IsContent
    0.52
     pran
    0.52
     Talvez
    0.52
     utafitiHapana
    0.51
    Activations Density 0.493%

    No Known Activations