INDEX

Explanations

words and punctuation related to the logical flow of an argument

oai_token-act-pair · gemini-2.0-flash

and

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

 CreateTagHelper

-0.81

dafx

-0.77

RenderAtEndOf

-0.76

UIControlState

-0.75

tonode

-0.74

HasForeignKey

-0.73

География

-0.73

 تضيفلها

-0.71

phosa

-0.71

 Rhodesia

-0.71

POSITIVE LOGITS

the

0.58

peta

0.52

 بگ

0.49

<bos>

0.48

 that

0.47

 where

0.47

raise

0.46

割

0.44

 Kapp

0.43

 resulting

0.43

Activations Density 5.677%

words and punctuation related to the logical flow of an argument

and

No Comments

No Known Activations