INDEX

Explanations

the word "Little"

oai_token-act-pair · gemini-2.0-flash

Little

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

 Small

-0.91

 small

-0.91

Small

-0.88

small

-0.84

 SMALL

-0.77

SMALL

-0.73

 petites

-0.68

 petits

-0.68

 tiny

-0.65

 petit

-0.61

POSITIVE LOGITS

AddTagHelper

0.94

IVEREF

0.91

 ujednoznacz

0.89

脚注の使い方

0.88

ContentAsync

0.85

 Audiodateien

0.84

GOTREF

0.84

 المعيارى

0.83

MigrationBuilder

0.82

 AssemblyTitle

0.79

Activations Density 0.975%

the word "Little"

Little

No Comments

No Known Activations