INDEX

Explanations

uses of measure words such as much, more, and little, as well as references to money or taxes

oai_token-act-pair · gemini-2.0-flash

Abstract concepts

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

 internetowa

-0.75

@[+][

-0.69

 ReactDOM

-0.64

migrationBuilder

-0.60

 <>",

-0.57

fficients

-0.56

 SwitchCompat

-0.56

 propOrder

-0.56

pulumi

-0.55

scriptcase

-0.55

POSITIVE LOGITS

 pressure

0.95

 respect

0.87

 support

0.85

 progress

0.83

 reverence

0.82

 control

0.80

 knowledge

0.79

 influence

0.79

 comfort

0.79

support

0.78

Activations Density 27.323%

uses of measure words such as much, more, and little, as well as references to money or taxes

Abstract concepts

No Comments

No Known Activations