INDEX

Explanations

words used when someone is trying to figure out what is going on.

oai_token-act-pair · gemini-2.0-flash

Common sentence structure tokens

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.98

-0.65

 CreateTagHelper

-0.60

 autorytatywna

-0.52

UnitTesting

-0.52

ISupport

-0.51

(+

-0.49

Personensuche

-0.48

-0.47

(.

-0.46

POSITIVE LOGITS

 This

0.66

\\\\

0.64

But

0.63

⎣

0.62

 That

0.61

0.60

↵↵

0.60

AutoScaleMode

0.60

','

0.60

Activations Density 22.311%

words used when someone is trying to figure out what is going on.

Common sentence structure tokens

No Comments

No Known Activations