INDEX

Explanations

words and phrases from a variety of different contexts, including sports, software, and health

oai_token-act-pair · gemini-2.0-flash

technical document excerpts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 незавершена

-0.64

principalTable

-0.63

Efq

-0.63

 againſt

-0.62

saraba

-0.62

 pylint

-0.61

 horns

-0.60

 iſt

-0.60

TagMode

-0.59

RunAsync

-0.59

POSITIVE LOGITS

Ar

0.49

endwhile

0.44

TabIndex

0.43

Revenir

0.43

ar

0.43

 FICTION

0.43

 AssemblyTitle

0.41

 presentarse

0.41

 jack

0.40

drawString

0.40

Activations Density 1.900%

words and phrases from a variety of different contexts, including sports, software, and health

technical document excerpts

No Comments

No Known Activations