INDEX

Explanations

code snippets with keywords such as "unable", "error", and "parsing" and words related to programming languages and data structures

oai_token-act-pair · gemini-2.0-flash

to

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

ValueStyle

-0.93

ⓧ

-0.66

RenderAtEndOf

-0.62

Hochspringen

-0.60

lottes

-0.57

AddTagHelper

-0.57

 المعيارى

-0.57

Atsauces

-0.53

ècie

-0.51

MessageState

-0.50

POSITIVE LOGITS

الإنجليزية

0.56

toBeTruthy

0.53

 getenv

0.48

theoremstyle

0.47

 végétale

0.47

'{@

0.46

 getEmail

0.46

 getView

0.46

 Bulbs

0.46

bereitung

0.46

Activations Density 14.429%

code snippets with keywords such as "unable", "error", and "parsing" and words related to programming languages and data structures

to

No Comments

No Known Activations