INDEX

Explanations

the word "cup"

oai_token-act-pair · gemini-2.0-flash

cup

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

<bos>

-1.20

 sauvages

-0.68

-0.65

The

-0.65

-0.61

-0.59

-0.57

 difficiles

-0.57

 ouvertes

-0.57

 picioare

-0.57

POSITIVE LOGITS

tvguidetime

0.98

ConstraintMaker

0.98

 виправивши

0.92

GRANTED

0.92

 CreateTagHelper

0.87

UserScript

0.82

__(/*!

0.82

SequentialGroup

0.82

ientôt

0.82

 initComponents

0.81

Activations Density 0.912%

the word "cup"

cup

No Comments

No Known Activations