© 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. 11269
    Prev
    Next
    INDEX
    Explanations

    the phrase "feel free"

    oai_token-act-pair · gemini-2.0-flash

    granting permission/freedom

    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
     الحره
    -0.94
     définiti
    -0.91
    BufferException
    -0.91
    featureID
    -0.88
     beginnetje
    -0.88
    +#+#
    -0.86
     ProtoMessage
    -0.82
    WebVitals
    -0.82
     تضيفلها
    -0.82
    ंदीखरीदारी
    -0.81
    POSITIVE LOGITS
     able
    0.39
    CJK
    0.35
    ety
    0.33
    el
    0.33
    tier
    0.33
     sẻ
    0.32
    vise
    0.31
     to
    0.30
    ']);
    0.29
     No
    0.28
    Activations Density 0.444%

    No Known Activations