INDEX

Explanations

numbered items in lists

oai_token-act-pair · gemini-2.0-flash

Foreign words

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

inte

-0.53

"](

-0.52

pri

-0.51

awtextra

-0.50

ra

-0.49

lib

-0.47

 noDo

-0.46

là

-0.46

gri

-0.46

<bos>

-0.45

POSITIVE LOGITS

TemporalType

0.79

 imprimée

0.71

 Shakspeare

0.68

 berätt

0.65

tagHelperRunner

0.62

 culoare

0.62

 وتسجيلات

0.61

 fidélité

0.61

 محفوظة

0.60

 bäst

0.60

Activations Density 9.996%

numbered items in lists

Foreign words

No Comments

No Known Activations