INDEX

Explanations

the word "present" or the word "left" or inflected forms thereof

oai_token-act-pair · gemini-2.0-flash

descriptions and analysis

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ConstraintMaker

-0.96

 tombé

-0.95

 éditoriale

-0.86

 समीक्षक

-0.85

 réunis

-0.82

 laiss

-0.82

IndentedString

-0.82

 <>",

-0.82

 occupé

-0.81

TagHelper

-0.81

POSITIVE LOGITS

0.61

↵↵

0.59

´

0.56

 labor

0.50

↵

0.50

 favorable

0.50

ByDefault

0.46

 characterizing

0.45

 favor

0.43

 stabilized

0.43

Activations Density 1.037%

the word "present" or the word "left" or inflected forms thereof

descriptions and analysis

No Comments

No Known Activations