INDEX

Explanations

words related to specialized or technical terminology

oai_token-act-pair · gemini-2.0-flash

group

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ỡng

-1.04

GEBURTSDATUM

-1.04

LookAnd

-0.99

MigrationBuilder

-0.96

 OFDb

-0.93

 समीक्षाओं

-0.93

 виправивши

-0.91

queryInterface

-0.90

 initComponents

-0.90

 intptr

-0.89

POSITIVE LOGITS

tetten

0.41

 Zamora

0.37

inburgh

0.37

沂

0.34

dificio

0.34

zmán

0.34

Especies

0.34

 Bahnhof

0.33

IBLE

0.33

oglobulin

0.33

Activations Density 4.123%

words related to specialized or technical terminology

group

No Comments

No Known Activations