INDEX

Explanations

code and unique identifiers

oai_token-act-pair · gemini-2.0-flash

="_

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-1.33

-1.19

ii

-1.00

ii

-0.94

ｉ

-0.93

Ii

-0.87

ni

-0.80

ih

-0.79

iI

-0.79

IE

-0.78

POSITIVE LOGITS

 GenerationType

0.58

ſelf

0.54

StoryboardSegue

0.54

enedor

0.54

 Theſe

0.53

 leſs

0.53

Abp

0.52

 ſeveral

0.52

 ſch

0.52

Становништво

0.52

Activations Density 29.479%

code and unique identifiers

="_

No Comments

No Known Activations