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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14161
    Prev
    Next
    INDEX
    Explanations

    lines of code with some indentation

    oai_token-act-pair · gemini-2.0-flash

    non-English characters

    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
    2
    -0.96
    3
    -0.70
    Rüyada
    -0.57
     незавершена
    -0.55
    Παραπομπές
    -0.55
     OMITBAD
    -0.54
     resourceCulture
    -0.54
     viewDidLoad
    -0.53
     doInBackground
    -0.51
    tagHelperRunner
    -0.51
    POSITIVE LOGITS
    ⓧ
    0.67
    GraphicsUnit
    0.59
    省市镇
    0.53
    슷
    0.49
     täv
    0.49
    ])),
    0.47
    mmate
    0.47
     själva
    0.46
     réguli
    0.46
    UINTN
    0.46
    Activations Density 0.807%

    No Known Activations