INDEX

Explanations

acronyms and the words associated with them.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Paglinawan

-1.09

expandindo

-0.90

WithIOException

-0.86

 ExecuteAsync

-0.81

ыгана

-0.80

complexContent

-0.79

 تضيفلها

-0.78

ThroughAttribute

-0.77

ivably

-0.77

 AssemblyCompany

-0.77

POSITIVE LOGITS

 ujednoznacz

0.46

<bos>

0.44

âmara

0.36

CodeAttribute

0.34

ざ

0.33

sat

0.33

origen

0.33

faktor

0.33

 program

0.32

 provis

0.32

Activations Density 0.713%

acronyms and the words associated with them.

No Comments

No Known Activations