INDEX

Explanations

words related to scoring in sports or politics

oai_token-act-pair · gemini-2.0-flash

decision-making

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

UnsafeEnabled

-0.90

MethodManager

-0.82

tagHelperRunner

-0.77

AndEndTag

-0.71

webElement

-0.71

 ModelExpression

-0.71

__":

-0.69

 InputDecoration

-0.68

ThroughAttribute

-0.67

adaptiveStyles

-0.65

POSITIVE LOGITS

 decisive

1.27

 deciding

1.26

 decide

1.03

 determining

0.98

 decisi

0.96

 decides

0.94

 Entscheidung

0.93

 decisivo

0.92

決定

0.90

decide

0.90

Activations Density 1.198%

words related to scoring in sports or politics

decision-making

No Comments

No Known Activations