INDEX

Explanations

scientific or academic style writing about species, locations, or types

oai_token-act-pair · gemini-2.0-flash

-wide

np_token-act-pair-logits · gemini-2.0-flash

Institutions and research

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Roskov

-0.54

الحياه

-0.53

 urbanos

-0.51

AddTagHelper

-0.49

ırken

-0.44

 artikkelen

-0.44

nenie

-0.43

owano

-0.42

spunkt

-0.42

enterOuterAlt

-0.42

POSITIVE LOGITS

wide

0.88

WIDE

0.79

ScopeManager

0.69

 WIDE

0.69

DockStyle

0.68

 wide

0.67

Wide

0.66

.*")]

0.63

 ogó

0.62

[]:

0.60

Activations Density 2.306%

scientific or academic style writing about species, locations, or types

-wide

Institutions and research

No Comments

No Known Activations