INDEX

Explanations

programming code snippets referencing specific technologies and error reports written in Japanese

oai_token-act-pair · gemini-2.0-flash

non-english text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

+#+#

-1.05

 CreateTagHelper

-0.85

esez

-0.75

Personendaten

-0.75

elemField

-0.73

ParallelGroup

-0.71

yarnpkg

-0.70

 propOrder

-0.69

ApiModelProperty

-0.68

errHandler

-0.67

POSITIVE LOGITS

 culturelles

0.56

 fédé

0.42

 financières

0.40

 brancas

0.40

 étrangères

0.38

 suya

0.38

 narod

0.36

 Produits

0.35

SUCCEEDED

0.35

eseorang

0.35

Activations Density 0.301%

programming code snippets referencing specific technologies and error reports written in Japanese

non-english text

No Comments

No Known Activations