© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9166
    Prev
    Next
    INDEX
    Explanations

    names of organizations and related words

    oai_token-act-pair · gemini-2.0-flash

    institution descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ⓧ
    -0.60
    atguigu
    -0.58
     LUMP
    -0.51
    RSpec
    -0.49
     defaultstate
    -0.49
     []:
    -0.49
    +#+#
    -0.49
    הערות
    -0.47
    WSGI
    -0.46
     caret
    -0.46
    POSITIVE LOGITS
    InputTagHelper
    0.67
    contentLoaded
    0.59
    )++;
    0.57
     تضيف
    0.55
    zczegól
    0.54
    FontOfSize
    0.54
     היתה
    0.52
    handleClose
    0.52
     eventdata
    0.52
    PyExc
    0.51
    Activations Density 4.285%

    No Known Activations