INDEX

Explanations

legal and programming terms

oai_token-act-pair · gemini-2.0-flash

Legal documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ChildScrollView

-0.83

новништво

-0.77

 chi̍t

-0.68

ValueGeneration

-0.65

DOCTYPE

-0.64

initializeApp

-0.64

UseVisualStyle

-0.63

GeneratedMessage

-0.62

Xna

-0.62

MigrationBuilder

-0.60

POSITIVE LOGITS

issory

0.50

lossary

0.49

ONCE

0.48

 benzina

0.48

 ricc

0.48

 betul

0.47

 pasada

0.45

 creativa

0.44

sihkan

0.44

 Heinemann

0.43

Activations Density 3.420%

legal and programming terms

Legal documents

No Comments

No Known Activations