INDEX

Explanations

legal documents or religious texts

oai_token-act-pair · gemini-2.0-flash

legal terms and actions

np_token-act-pair-logits · gpt-4o-mini

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 getting

-1.01

 taking

-0.97

 making

-0.95

 being

-0.93

 fiind

-0.86

 giving

-0.86

 providing

-0.85

 enjoying

-0.85

 putting

-0.84

 sendo

-0.84

POSITIVE LOGITS

 evacuate

0.56

polate

0.54

 fasse

0.53

 sağlar

0.53

uarkan

0.53

 activate

0.53

activate

0.52

 kullanılır

0.52

 SwitchCompat

0.52

 disediakan

0.52

Activations Density 1.352%

legal documents or religious texts

legal terms and actions

No Comments

No Known Activations