© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13759
    Prev
    Next
    INDEX
    Explanations

    text related to cryptography and network security

    oai_token-act-pair · gemini-2.0-flash

    SSH keys and cryptography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    gram
    -0.40
     대해
    -0.40
     communication
    -0.40
    grams
    -0.39
     communicate
    -0.38
     acety
    -0.38
     omnia
    -0.38
     PopupWindow
    -0.37
    IONE
    -0.37
     Neve
    -0.36
    POSITIVE LOGITS
    tvguidetime
    0.76
     ModelExpression
    0.76
    GRANTED
    0.65
     مشين
    0.61
     للاسماء
    0.60
    Parcelize
    0.60
    titleMargin
    0.59
     MotionEvent
    0.59
    ellees
    0.58
     utafitiHapana
    0.57
    Activations Density 1.589%

    No Known Activations