INDEX

Explanations

a mix of pronouns, numbered lists, scientific or legal terms, and references to portions of things.

oai_token-act-pair · gemini-2.0-flash

French words

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

 بيها

-0.72

use

-0.65

 choose

-0.64

 reckon

-0.64

期刊论文

-0.61

 consider

-0.59

Use

-0.58

 SwiftUI

-0.58

 forget

-0.57

 realize

-0.57

POSITIVE LOGITS

 étoit

0.61

 auroit

0.61

 avoient

0.56

__":

0.53

 feroit

0.52

 aimez

0.51

 occhiali

0.50

contentLoaded

0.49

 nuages

0.46

 copertura

0.45

Activations Density 4.427%

a mix of pronouns, numbered lists, scientific or legal terms, and references to portions of things.

French words

No Comments

No Known Activations