© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9710
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to security or locking mechanisms in both digital and physical contexts

    oai_token-act-pair · gemini-2.0-flash

    lock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     lock
    -2.81
     Lock
    -2.59
    lock
    -2.47
    Lock
    -2.42
     LOCK
    -2.36
     locks
    -2.25
    LOCK
    -2.19
     locked
    -2.11
     locking
    -2.08
    locks
    -2.00
    POSITIVE LOGITS
    Попис
    0.71
     المعيارى
    0.50
     aérienne
    0.47
    daq
    0.47
    tedrale
    0.45
    uterte
    0.45
     везе
    0.44
     dysplasia
    0.44
     brille
    0.43
     Arles
    0.43
    Activations Density 20.201%

    No Known Activations